case study content analysis

Have a language expert improve your writing

Run a free plagiarism check in 10 minutes, automatically generate references for free.

• Knowledge Base
• Methodology

Content Analysis | A Step-by-Step Guide with Examples

Published on 5 May 2022 by Amy Luo . Revised on 5 December 2022.

Content analysis is a research method used to identify patterns in recorded communication. To conduct content analysis, you systematically collect data from a set of texts, which can be written, oral, or visual:

• Books, newspapers, and magazines
• Speeches and interviews
• Web content and social media posts
• Photographs and films

Content analysis can be both quantitative (focused on counting and measuring) and qualitative (focused on interpreting and understanding). In both types, you categorise or ‘code’ words, themes, and concepts within the texts and then analyse the results.

Table of contents

What is content analysis used for, advantages of content analysis, disadvantages of content analysis, how to conduct content analysis.

Researchers use content analysis to find out about the purposes, messages, and effects of communication content. They can also make inferences about the producers and audience of the texts they analyse.

Content analysis can be used to quantify the occurrence of certain words, phrases, subjects, or concepts in a set of historical or contemporary texts.

In addition, content analysis can be used to make qualitative inferences by analysing the meaning and semantic relationship of words and concepts.

Because content analysis can be applied to a broad range of texts, it is used in a variety of fields, including marketing, media studies, anthropology, cognitive science, psychology, and many social science disciplines. It has various possible goals:

• Finding correlations and patterns in how concepts are communicated
• Understanding the intentions of an individual, group, or institution
• Identifying propaganda and bias in communication
• Revealing differences in communication in different contexts
• Analysing the consequences of communication content, such as the flow of information or audience responses

Prevent plagiarism, run a free check.

• Unobtrusive data collection

You can analyse communication and social interaction without the direct involvement of participants, so your presence as a researcher doesn’t influence the results.

• Transparent and replicable

When done well, content analysis follows a systematic procedure that can easily be replicated by other researchers, yielding results with high reliability .

• Highly flexible

You can conduct content analysis at any time, in any location, and at low cost. All you need is access to the appropriate sources.

Focusing on words or phrases in isolation can sometimes be overly reductive, disregarding context, nuance, and ambiguous meanings.

Content analysis almost always involves some level of subjective interpretation, which can affect the reliability and validity of the results and conclusions.

• Time intensive

Manually coding large volumes of text is extremely time-consuming, and it can be difficult to automate effectively.

If you want to use content analysis in your research, you need to start with a clear, direct  research question .

Next, you follow these five steps.

Step 1: Select the content you will analyse

Based on your research question, choose the texts that you will analyse. You need to decide:

• The medium (e.g., newspapers, speeches, or websites) and genre (e.g., opinion pieces, political campaign speeches, or marketing copy)
• The criteria for inclusion (e.g., newspaper articles that mention a particular event, speeches by a certain politician, or websites selling a specific type of product)
• The parameters in terms of date range, location, etc.

If there are only a small number of texts that meet your criteria, you might analyse all of them. If there is a large volume of texts, you can select a sample .

Step 2: Define the units and categories of analysis

Next, you need to determine the level at which you will analyse your chosen texts. This means defining:

• The unit(s) of meaning that will be coded. For example, are you going to record the frequency of individual words and phrases, the characteristics of people who produced or appear in the texts, the presence and positioning of images, or the treatment of themes and concepts?
• The set of categories that you will use for coding. Categories can be objective characteristics (e.g., aged 30–40, lawyer, parent) or more conceptual (e.g., trustworthy, corrupt, conservative, family-oriented).

Step 3: Develop a set of rules for coding

Coding involves organising the units of meaning into the previously defined categories. Especially with more conceptual categories, it’s important to clearly define the rules for what will and won’t be included to ensure that all texts are coded consistently.

Coding rules are especially important if multiple researchers are involved, but even if you’re coding all of the text by yourself, recording the rules makes your method more transparent and reliable.

Step 4: Code the text according to the rules

You go through each text and record all relevant data in the appropriate categories. This can be done manually or aided with computer programs, such as QSR NVivo , Atlas.ti , and Diction , which can help speed up the process of counting and categorising words and phrases.

Step 5: Analyse the results and draw conclusions

Once coding is complete, the collected data is examined to find patterns and draw conclusions in response to your research question. You might use statistical analysis to find correlations or trends, discuss your interpretations of what the results mean, and make inferences about the creators, context, and audience of the texts.

Cite this Scribbr article

If you want to cite this source, you can copy and paste the citation or click the ‘Cite this Scribbr article’ button to automatically add the citation to our free Reference Generator.

Luo, A. (2022, December 05). Content Analysis | A Step-by-Step Guide with Examples. Scribbr. Retrieved 22 April 2024, from https://www.scribbr.co.uk/research-methods/content-analysis-explained/

Is this article helpful?

Other students also liked

How to do thematic analysis | guide & examples, data collection methods | step-by-step guide & examples, qualitative vs quantitative research | examples & methods.

What Is Qualitative Content Analysis?

Qca explained simply (with examples).

By: Jenna Crosley (PhD). Reviewed by: Dr Eunice Rautenbach (DTech) | February 2021

If you’re in the process of preparing for your dissertation, thesis or research project, you’ve probably encountered the term “ qualitative content analysis ” – it’s quite a mouthful. If you’ve landed on this post, you’re probably a bit confused about it. Well, the good news is that you’ve come to the right place…

Overview: Qualitative Content Analysis

• What (exactly) is qualitative content analysis
• The two main types of content analysis
• When to use content analysis
• How to conduct content analysis (the process)
• The advantages and disadvantages of content analysis

1. What is content analysis?

Content analysis is a  qualitative analysis method  that focuses on recorded human artefacts such as manuscripts, voice recordings and journals. Content analysis investigates these written, spoken and visual artefacts without explicitly extracting data from participants – this is called  unobtrusive  research.

In other words, with content analysis, you don’t necessarily need to interact with participants (although you can if necessary); you can simply analyse the data that they have already produced. With this type of analysis, you can analyse data such as text messages, books, Facebook posts, videos, and audio (just to mention a few).

The basics – explicit and implicit content

When working with content analysis, explicit and implicit content will play a role. Explicit data is transparent and easy to identify, while implicit data is that which requires some form of interpretation and is often of a subjective nature. Sounds a bit fluffy? Here’s an example:

Joe: Hi there, what can I help you with? 

Lauren: I recently adopted a puppy and I’m worried that I’m not feeding him the right food. Could you please advise me on what I should be feeding? 

Joe: Sure, just follow me and I’ll show you. Do you have any other pets?

Lauren: Only one, and it tweets a lot!

In this exchange, the explicit data indicates that Joe is helping Lauren to find the right puppy food. Lauren asks Joe whether she has any pets aside from her puppy. This data is explicit because it requires no interpretation.

On the other hand, implicit data , in this case, includes the fact that the speakers are in a pet store. This information is not clearly stated but can be inferred from the conversation, where Joe is helping Lauren to choose pet food. An additional piece of implicit data is that Lauren likely has some type of bird as a pet. This can be inferred from the way that Lauren states that her pet “tweets”.

As you can see, explicit and implicit data both play a role in human interaction  and are an important part of your analysis. However, it’s important to differentiate between these two types of data when you’re undertaking content analysis. Interpreting implicit data can be rather subjective as conclusions are based on the researcher’s interpretation. This can introduce an element of bias , which risks skewing your results.

2. The two types of content analysis

Now that you understand the difference between implicit and explicit data, let’s move on to the two general types of content analysis : conceptual and relational content analysis. Importantly, while conceptual and relational content analysis both follow similar steps initially, the aims and outcomes of each are different.

Conceptual analysis focuses on the number of times a concept occurs in a set of data and is generally focused on explicit data. For example, if you were to have the following conversation:

Marie: She told me that she has three cats.

Jean: What are her cats’ names?

Marie: I think the first one is Bella, the second one is Mia, and… I can’t remember the third cat’s name.

In this data, you can see that the word “cat” has been used three times. Through conceptual content analysis, you can deduce that cats are the central topic of the conversation. You can also perform a frequency analysis , where you assess the term’s frequency in the data. For example, in the exchange above, the word “cat” makes up 9% of the data. In other words, conceptual analysis brings a little bit of quantitative analysis into your qualitative analysis.

As you can see, the above data is without interpretation and focuses on explicit data . Relational content analysis, on the other hand, takes a more holistic view by focusing more on implicit data in terms of context, surrounding words and relationships.

There are three types of relational analysis:

• Affect extraction
• Proximity analysis
• Cognitive mapping

Affect extraction is when you assess concepts according to emotional attributes. These emotions are typically mapped on scales, such as a Likert scale or a rating scale ranging from 1 to 5, where 1 is “very sad” and 5 is “very happy”.

If participants are talking about their achievements, they are likely to be given a score of 4 or 5, depending on how good they feel about it. If a participant is describing a traumatic event, they are likely to have a much lower score, either 1 or 2.

Proximity analysis identifies explicit terms (such as those found in a conceptual analysis) and the patterns in terms of how they co-occur in a text. In other words, proximity analysis investigates the relationship between terms and aims to group these to extract themes and develop meaning.

Proximity analysis is typically utilised when you’re looking for hard facts rather than emotional, cultural, or contextual factors. For example, if you were to analyse a political speech, you may want to focus only on what has been said, rather than implications or hidden meanings. To do this, you would make use of explicit data, discounting any underlying meanings and implications of the speech.

Lastly, there’s cognitive mapping, which can be used in addition to, or along with, proximity analysis. Cognitive mapping involves taking different texts and comparing them in a visual format – i.e. a cognitive map. Typically, you’d use cognitive mapping in studies that assess changes in terms, definitions, and meanings over time. It can also serve as a way to visualise affect extraction or proximity analysis and is often presented in a form such as a graphic map.

To recap on the essentials, content analysis is a qualitative analysis method that focuses on recorded human artefacts . It involves both conceptual analysis (which is more numbers-based) and relational analysis (which focuses on the relationships between concepts and how they’re connected).

Need a helping hand?

3. When should you use content analysis?

Content analysis is a useful tool that provides insight into trends of communication . For example, you could use a discussion forum as the basis of your analysis and look at the types of things the members talk about as well as how they use language to express themselves. Content analysis is flexible in that it can be applied to the individual, group, and institutional level.

Content analysis is typically used in studies where the aim is to better understand factors such as behaviours, attitudes, values, emotions, and opinions . For example, you could use content analysis to investigate an issue in society, such as miscommunication between cultures. In this example, you could compare patterns of communication in participants from different cultures, which will allow you to create strategies for avoiding misunderstandings in intercultural interactions.

Another example could include conducting content analysis on a publication such as a book. Here you could gather data on the themes, topics, language use and opinions reflected in the text to draw conclusions regarding the political (such as conservative or liberal) leanings of the publication.

4. How to conduct a qualitative content analysis

Conceptual and relational content analysis differ in terms of their exact process ; however, there are some similarities. Let’s have a look at these first – i.e., the generic process:

• Recap on your research questions
• Undertake bracketing to identify biases
• Operationalise your variables and develop a coding scheme
• Code the data and undertake your analysis

Step 1 – Recap on your research questions

It’s always useful to begin a project with research questions , or at least with an idea of what you are looking for. In fact, if you’ve spent time reading this blog, you’ll know that it’s useful to recap on your research questions, aims and objectives when undertaking pretty much any research activity. In the context of content analysis, it’s difficult to know what needs to be coded and what doesn’t, without a clear view of the research questions.

For example, if you were to code a conversation focused on basic issues of social justice, you may be met with a wide range of topics that may be irrelevant to your research. However, if you approach this data set with the specific intent of investigating opinions on gender issues, you will be able to focus on this topic alone, which would allow you to code only what you need to investigate.

Step 2 – Reflect on your personal perspectives and biases

It’s vital that you reflect on your own pre-conception of the topic at hand and identify the biases that you might drag into your content analysis – this is called “ bracketing “. By identifying this upfront, you’ll be more aware of them and less likely to have them subconsciously influence your analysis.

For example, if you were to investigate how a community converses about unequal access to healthcare, it is important to assess your views to ensure that you don’t project these onto your understanding of the opinions put forth by the community. If you have access to medical aid, for instance, you should not allow this to interfere with your examination of unequal access.

Step 3 – Operationalise your variables and develop a coding scheme

Next, you need to operationalise your variables . But what does that mean? Simply put, it means that you have to define each variable or construct . Give every item a clear definition – what does it mean (include) and what does it not mean (exclude). For example, if you were to investigate children’s views on healthy foods, you would first need to define what age group/range you’re looking at, and then also define what you mean by “healthy foods”.

In combination with the above, it is important to create a coding scheme , which will consist of information about your variables (how you defined each variable), as well as a process for analysing the data. For this, you would refer back to how you operationalised/defined your variables so that you know how to code your data.

For example, when coding, when should you code a food as “healthy”? What makes a food choice healthy? Is it the absence of sugar or saturated fat? Is it the presence of fibre and protein? It’s very important to have clearly defined variables to achieve consistent coding – without this, your analysis will get very muddy, very quickly.

Step 4 – Code and analyse the data

The next step is to code the data. At this stage, there are some differences between conceptual and relational analysis.

As described earlier in this post, conceptual analysis looks at the existence and frequency of concepts, whereas a relational analysis looks at the relationships between concepts. For both types of analyses, it is important to pre-select a concept that you wish to assess in your data. Using the example of studying children’s views on healthy food, you could pre-select the concept of “healthy food” and assess the number of times the concept pops up in your data.

Here is where conceptual and relational analysis start to differ.

At this stage of conceptual analysis , it is necessary to decide on the level of analysis you’ll perform on your data, and whether this will exist on the word, phrase, sentence, or thematic level. For example, will you code the phrase “healthy food” on its own? Will you code each term relating to healthy food (e.g., broccoli, peaches, bananas, etc.) with the code “healthy food” or will these be coded individually? It is very important to establish this from the get-go to avoid inconsistencies that could result in you having to code your data all over again.

On the other hand, relational analysis looks at the type of analysis. So, will you use affect extraction? Proximity analysis? Cognitive mapping? A mix? It’s vital to determine the type of analysis before you begin to code your data so that you can maintain the reliability and validity of your research .

How to conduct conceptual analysis

First, let’s have a look at the process for conceptual analysis.

Once you’ve decided on your level of analysis, you need to establish how you will code your concepts, and how many of these you want to code. Here you can choose whether you want to code in a deductive or inductive manner. Just to recap, deductive coding is when you begin the coding process with a set of pre-determined codes, whereas inductive coding entails the codes emerging as you progress with the coding process. Here it is also important to decide what should be included and excluded from your analysis, and also what levels of implication you wish to include in your codes.

For example, if you have the concept of “tall”, can you include “up in the clouds”, derived from the sentence, “the giraffe’s head is up in the clouds” in the code, or should it be a separate code? In addition to this, you need to know what levels of words may be included in your codes or not. For example, if you say, “the panda is cute” and “look at the panda’s cuteness”, can “cute” and “cuteness” be included under the same code?

Once you’ve considered the above, it’s time to code the text . We’ve already published a detailed post about coding , so we won’t go into that process here. Once you’re done coding, you can move on to analysing your results. This is where you will aim to find generalisations in your data, and thus draw your conclusions .

How to conduct relational analysis

Now let’s return to relational analysis.

As mentioned, you want to look at the relationships between concepts . To do this, you’ll need to create categories by reducing your data (in other words, grouping similar concepts together) and then also code for words and/or patterns. These are both done with the aim of discovering whether these words exist, and if they do, what they mean.

Your next step is to assess your data and to code the relationships between your terms and meanings, so that you can move on to your final step, which is to sum up and analyse the data.

To recap, it’s important to start your analysis process by reviewing your research questions and identifying your biases . From there, you need to operationalise your variables, code your data and then analyse it.

5. What are the pros & cons of content analysis?

One of the main advantages of content analysis is that it allows you to use a mix of quantitative and qualitative research methods, which results in a more scientifically rigorous analysis.

For example, with conceptual analysis, you can count the number of times that a term or a code appears in a dataset, which can be assessed from a quantitative standpoint. In addition to this, you can then use a qualitative approach to investigate the underlying meanings of these and relationships between them.

Content analysis is also unobtrusive and therefore poses fewer ethical issues than some other analysis methods. As the content you’ll analyse oftentimes already exists, you’ll analyse what has been produced previously, and so you won’t have to collect data directly from participants. When coded correctly, data is analysed in a very systematic and transparent manner, which means that issues of replicability (how possible it is to recreate research under the same conditions) are reduced greatly.

On the downside , qualitative research (in general, not just content analysis) is often critiqued for being too subjective and for not being scientifically rigorous enough. This is where reliability (how replicable a study is by other researchers) and validity (how suitable the research design is for the topic being investigated) come into play – if you take these into account, you’ll be on your way to achieving sound research results.

Recap: Qualitative content analysis

In this post, we’ve covered a lot of ground – click on any of the sections to recap:

If you have any questions about qualitative content analysis, feel free to leave a comment below. If you’d like 1-on-1 help with your qualitative content analysis, be sure to book an initial consultation with one of our friendly Research Coaches.

Psst... there’s more!

This post was based on one of our popular Research Bootcamps . If you're working on a research project, you'll definitely want to check this out ...

You Might Also Like:

14 Comments

If I am having three pre-decided attributes for my research based on which a set of semi-structured questions where asked then should I conduct a conceptual content analysis or relational content analysis. please note that all three attributes are different like Agility, Resilience and AI.

Thank you very much. I really enjoyed every word.

please send me one/ two sample of content analysis

send me to any sample of qualitative content analysis as soon as possible

Many thanks for the brilliant explanation. Do you have a sample practical study of a foreign policy using content analysis?

1) It will be very much useful if a small but complete content analysis can be sent, from research question to coding and analysis. 2) Is there any software by which qualitative content analysis can be done?

Common software for qualitative analysis is nVivo, and quantitative analysis is IBM SPSS

Thank you. Can I have at least 2 copies of a sample analysis study as my reference?

Could you please send me some sample of textbook content analysis?

Can I send you my research topic, aims, objectives and questions to give me feedback on them?

please could you send me samples of content analysis?

Yes please send

really we enjoyed your knowledge thanks allot. from Ethiopia

can you please share some samples of content analysis(relational)? I am a bit confused about processing the analysis part

Submit a Comment Cancel reply

Your email address will not be published. Required fields are marked *

Save my name, email, and website in this browser for the next time I comment.

• Print Friendly

• Search Menu
• Browse content in Arts and Humanities
• Browse content in Archaeology
• Anglo-Saxon and Medieval Archaeology
• Archaeological Methodology and Techniques
• Archaeology by Region
• Archaeology of Religion
• Archaeology of Trade and Exchange
• Biblical Archaeology
• Contemporary and Public Archaeology
• Environmental Archaeology
• Historical Archaeology
• History and Theory of Archaeology
• Industrial Archaeology
• Landscape Archaeology
• Mortuary Archaeology
• Prehistoric Archaeology
• Underwater Archaeology
• Urban Archaeology
• Zooarchaeology
• Browse content in Architecture
• Architectural Structure and Design
• History of Architecture
• Residential and Domestic Buildings
• Theory of Architecture
• Browse content in Art
• Art Subjects and Themes
• History of Art
• Industrial and Commercial Art
• Theory of Art
• Biographical Studies
• Byzantine Studies
• Browse content in Classical Studies
• Classical History
• Classical Philosophy
• Classical Mythology
• Classical Literature
• Classical Reception
• Classical Art and Architecture
• Classical Oratory and Rhetoric
• Greek and Roman Epigraphy
• Greek and Roman Law
• Greek and Roman Archaeology
• Greek and Roman Papyrology
• Late Antiquity
• Religion in the Ancient World
• Digital Humanities
• Browse content in History
• Colonialism and Imperialism
• Diplomatic History
• Environmental History
• Genealogy, Heraldry, Names, and Honours
• Genocide and Ethnic Cleansing
• Historical Geography
• History by Period
• History of Agriculture
• History of Education
• History of Emotions
• History of Gender and Sexuality
• Industrial History
• Intellectual History
• International History
• Labour History
• Legal and Constitutional History
• Local and Family History
• Maritime History
• Military History
• National Liberation and Post-Colonialism
• Oral History
• Political History
• Public History
• Regional and National History
• Revolutions and Rebellions
• Slavery and Abolition of Slavery
• Social and Cultural History
• Theory, Methods, and Historiography
• Urban History
• World History
• Browse content in Language Teaching and Learning
• Language Learning (Specific Skills)
• Language Teaching Theory and Methods
• Browse content in Linguistics
• Applied Linguistics
• Cognitive Linguistics
• Computational Linguistics
• Forensic Linguistics
• Grammar, Syntax and Morphology
• Historical and Diachronic Linguistics
• History of English
• Language Acquisition
• Language Variation
• Language Families
• Language Evolution
• Language Reference
• Lexicography
• Linguistic Theories
• Linguistic Typology
• Linguistic Anthropology
• Phonetics and Phonology
• Psycholinguistics
• Sociolinguistics
• Translation and Interpretation
• Writing Systems
• Browse content in Literature
• Bibliography
• Children's Literature Studies
• Literary Studies (Asian)
• Literary Studies (European)
• Literary Studies (Eco-criticism)
• Literary Studies (Modernism)
• Literary Studies (Romanticism)
• Literary Studies (American)
• Literary Studies - World
• Literary Studies (1500 to 1800)
• Literary Studies (19th Century)
• Literary Studies (20th Century onwards)
• Literary Studies (African American Literature)
• Literary Studies (British and Irish)
• Literary Studies (Early and Medieval)
• Literary Studies (Fiction, Novelists, and Prose Writers)
• Literary Studies (Gender Studies)
• Literary Studies (Graphic Novels)
• Literary Studies (History of the Book)
• Literary Studies (Plays and Playwrights)
• Literary Studies (Poetry and Poets)
• Literary Studies (Postcolonial Literature)
• Literary Studies (Queer Studies)
• Literary Studies (Science Fiction)
• Literary Studies (Travel Literature)
• Literary Studies (War Literature)
• Literary Studies (Women's Writing)
• Literary Theory and Cultural Studies
• Mythology and Folklore
• Shakespeare Studies and Criticism
• Browse content in Media Studies
• Browse content in Music
• Applied Music
• Dance and Music
• Ethics in Music
• Ethnomusicology
• Gender and Sexuality in Music
• Medicine and Music
• Music Cultures
• Music and Religion
• Music and Culture
• Music and Media
• Music Education and Pedagogy
• Music Theory and Analysis
• Musical Scores, Lyrics, and Libretti
• Musical Structures, Styles, and Techniques
• Musicology and Music History
• Performance Practice and Studies
• Race and Ethnicity in Music
• Sound Studies
• Browse content in Performing Arts
• Browse content in Philosophy
• Aesthetics and Philosophy of Art
• Epistemology
• Feminist Philosophy
• History of Western Philosophy
• Metaphysics
• Moral Philosophy
• Non-Western Philosophy
• Philosophy of Science
• Philosophy of Action
• Philosophy of Law
• Philosophy of Religion
• Philosophy of Language
• Philosophy of Mind
• Philosophy of Perception
• Philosophy of Mathematics and Logic
• Practical Ethics
• Social and Political Philosophy
• Browse content in Religion
• Biblical Studies
• Christianity
• East Asian Religions
• History of Religion
• Judaism and Jewish Studies
• Qumran Studies
• Religion and Education
• Religion and Health
• Religion and Politics
• Religion and Science
• Religion and Law
• Religion and Art, Literature, and Music
• Religious Studies
• Browse content in Society and Culture
• Cookery, Food, and Drink
• Cultural Studies
• Customs and Traditions
• Ethical Issues and Debates
• Hobbies, Games, Arts and Crafts
• Lifestyle, Home, and Garden
• Natural world, Country Life, and Pets
• Popular Beliefs and Controversial Knowledge
• Sports and Outdoor Recreation
• Technology and Society
• Travel and Holiday
• Visual Culture
• Browse content in Law
• Arbitration
• Browse content in Company and Commercial Law
• Commercial Law
• Company Law
• Browse content in Comparative Law
• Systems of Law
• Competition Law
• Browse content in Constitutional and Administrative Law
• Government Powers
• Judicial Review
• Local Government Law
• Military and Defence Law
• Parliamentary and Legislative Practice
• Construction Law
• Contract Law
• Browse content in Criminal Law
• Criminal Procedure
• Criminal Evidence Law
• Sentencing and Punishment
• Employment and Labour Law
• Environment and Energy Law
• Browse content in Financial Law
• Banking Law
• Insolvency Law
• History of Law
• Human Rights and Immigration
• Intellectual Property Law
• Browse content in International Law
• Private International Law and Conflict of Laws
• Public International Law
• IT and Communications Law
• Jurisprudence and Philosophy of Law
• Law and Politics
• Law and Society
• Browse content in Legal System and Practice
• Courts and Procedure
• Legal Skills and Practice
• Primary Sources of Law
• Regulation of Legal Profession
• Medical and Healthcare Law
• Browse content in Policing
• Criminal Investigation and Detection
• Police and Security Services
• Police Procedure and Law
• Police Regional Planning
• Browse content in Property Law
• Personal Property Law
• Study and Revision
• Terrorism and National Security Law
• Browse content in Trusts Law
• Wills and Probate or Succession
• Browse content in Medicine and Health
• Browse content in Allied Health Professions
• Arts Therapies
• Clinical Science
• Dietetics and Nutrition
• Occupational Therapy
• Operating Department Practice
• Physiotherapy
• Radiography
• Speech and Language Therapy
• Browse content in Anaesthetics
• General Anaesthesia
• Neuroanaesthesia
• Browse content in Clinical Medicine
• Acute Medicine
• Cardiovascular Medicine
• Clinical Genetics
• Clinical Pharmacology and Therapeutics
• Dermatology
• Endocrinology and Diabetes
• Gastroenterology
• Genito-urinary Medicine
• Geriatric Medicine
• Infectious Diseases
• Medical Oncology
• Medical Toxicology
• Pain Medicine
• Palliative Medicine
• Rehabilitation Medicine
• Respiratory Medicine and Pulmonology
• Rheumatology
• Sleep Medicine
• Sports and Exercise Medicine
• Clinical Neuroscience
• Community Medical Services
• Critical Care
• Emergency Medicine
• Forensic Medicine
• Haematology
• History of Medicine
• Browse content in Medical Dentistry
• Oral and Maxillofacial Surgery
• Paediatric Dentistry
• Restorative Dentistry and Orthodontics
• Surgical Dentistry
• Medical Ethics
• Browse content in Medical Skills
• Clinical Skills
• Communication Skills
• Nursing Skills
• Surgical Skills
• Medical Statistics and Methodology
• Browse content in Neurology
• Clinical Neurophysiology
• Neuropathology
• Nursing Studies
• Browse content in Obstetrics and Gynaecology
• Gynaecology
• Occupational Medicine
• Ophthalmology
• Otolaryngology (ENT)
• Browse content in Paediatrics
• Neonatology
• Browse content in Pathology
• Chemical Pathology
• Clinical Cytogenetics and Molecular Genetics
• Histopathology
• Medical Microbiology and Virology
• Patient Education and Information
• Browse content in Pharmacology
• Psychopharmacology
• Browse content in Popular Health
• Caring for Others
• Complementary and Alternative Medicine
• Self-help and Personal Development
• Browse content in Preclinical Medicine
• Cell Biology
• Molecular Biology and Genetics
• Reproduction, Growth and Development
• Primary Care
• Professional Development in Medicine
• Browse content in Psychiatry
• Addiction Medicine
• Child and Adolescent Psychiatry
• Forensic Psychiatry
• Learning Disabilities
• Old Age Psychiatry
• Psychotherapy
• Browse content in Public Health and Epidemiology
• Epidemiology
• Public Health
• Browse content in Radiology
• Clinical Radiology
• Interventional Radiology
• Nuclear Medicine
• Radiation Oncology
• Reproductive Medicine
• Browse content in Surgery
• Cardiothoracic Surgery
• Gastro-intestinal and Colorectal Surgery
• General Surgery
• Neurosurgery
• Paediatric Surgery
• Peri-operative Care
• Plastic and Reconstructive Surgery
• Surgical Oncology
• Transplant Surgery
• Trauma and Orthopaedic Surgery
• Vascular Surgery
• Browse content in Science and Mathematics
• Browse content in Biological Sciences
• Aquatic Biology
• Biochemistry
• Bioinformatics and Computational Biology
• Developmental Biology
• Ecology and Conservation
• Evolutionary Biology
• Genetics and Genomics
• Microbiology
• Molecular and Cell Biology
• Natural History
• Plant Sciences and Forestry
• Research Methods in Life Sciences
• Structural Biology
• Systems Biology
• Zoology and Animal Sciences
• Browse content in Chemistry
• Analytical Chemistry
• Computational Chemistry
• Crystallography
• Environmental Chemistry
• Industrial Chemistry
• Inorganic Chemistry
• Materials Chemistry
• Medicinal Chemistry
• Mineralogy and Gems
• Organic Chemistry
• Physical Chemistry
• Polymer Chemistry
• Study and Communication Skills in Chemistry
• Theoretical Chemistry
• Browse content in Computer Science
• Artificial Intelligence
• Computer Architecture and Logic Design
• Game Studies
• Human-Computer Interaction
• Mathematical Theory of Computation
• Programming Languages
• Software Engineering
• Systems Analysis and Design
• Virtual Reality
• Browse content in Computing
• Business Applications
• Computer Security
• Computer Games
• Computer Networking and Communications
• Digital Lifestyle
• Graphical and Digital Media Applications
• Operating Systems
• Browse content in Earth Sciences and Geography
• Atmospheric Sciences
• Environmental Geography
• Geology and the Lithosphere
• Maps and Map-making
• Meteorology and Climatology
• Oceanography and Hydrology
• Palaeontology
• Physical Geography and Topography
• Regional Geography
• Soil Science
• Urban Geography
• Browse content in Engineering and Technology
• Agriculture and Farming
• Biological Engineering
• Civil Engineering, Surveying, and Building
• Electronics and Communications Engineering
• Energy Technology
• Engineering (General)
• Environmental Science, Engineering, and Technology
• History of Engineering and Technology
• Mechanical Engineering and Materials
• Technology of Industrial Chemistry
• Transport Technology and Trades
• Browse content in Environmental Science
• Applied Ecology (Environmental Science)
• Conservation of the Environment (Environmental Science)
• Environmental Sustainability
• Environmentalist Thought and Ideology (Environmental Science)
• Management of Land and Natural Resources (Environmental Science)
• Natural Disasters (Environmental Science)
• Nuclear Issues (Environmental Science)
• Pollution and Threats to the Environment (Environmental Science)
• Social Impact of Environmental Issues (Environmental Science)
• History of Science and Technology
• Browse content in Materials Science
• Ceramics and Glasses
• Composite Materials
• Metals, Alloying, and Corrosion
• Nanotechnology
• Browse content in Mathematics
• Applied Mathematics
• Biomathematics and Statistics
• History of Mathematics
• Mathematical Education
• Mathematical Finance
• Mathematical Analysis
• Numerical and Computational Mathematics
• Probability and Statistics
• Pure Mathematics
• Browse content in Neuroscience
• Cognition and Behavioural Neuroscience
• Development of the Nervous System
• Disorders of the Nervous System
• History of Neuroscience
• Invertebrate Neurobiology
• Molecular and Cellular Systems
• Neuroendocrinology and Autonomic Nervous System
• Neuroscientific Techniques
• Sensory and Motor Systems
• Browse content in Physics
• Astronomy and Astrophysics
• Atomic, Molecular, and Optical Physics
• Biological and Medical Physics
• Classical Mechanics
• Computational Physics
• Condensed Matter Physics
• Electromagnetism, Optics, and Acoustics
• History of Physics
• Mathematical and Statistical Physics
• Measurement Science
• Nuclear Physics
• Particles and Fields
• Plasma Physics
• Quantum Physics
• Relativity and Gravitation
• Semiconductor and Mesoscopic Physics
• Browse content in Psychology
• Affective Sciences
• Clinical Psychology
• Cognitive Neuroscience
• Cognitive Psychology
• Criminal and Forensic Psychology
• Developmental Psychology
• Educational Psychology
• Evolutionary Psychology
• Health Psychology
• History and Systems in Psychology
• Music Psychology
• Neuropsychology
• Organizational Psychology
• Psychological Assessment and Testing
• Psychology of Human-Technology Interaction
• Psychology Professional Development and Training
• Research Methods in Psychology
• Social Psychology
• Browse content in Social Sciences
• Browse content in Anthropology
• Anthropology of Religion
• Human Evolution
• Medical Anthropology
• Physical Anthropology
• Regional Anthropology
• Social and Cultural Anthropology
• Theory and Practice of Anthropology
• Browse content in Business and Management
• Business Strategy
• Business History
• Business Ethics
• Business and Government
• Business and Technology
• Business and the Environment
• Comparative Management
• Corporate Governance
• Corporate Social Responsibility
• Entrepreneurship
• Health Management
• Human Resource Management
• Industrial and Employment Relations
• Industry Studies
• Information and Communication Technologies
• International Business
• Knowledge Management
• Management and Management Techniques
• Operations Management
• Organizational Theory and Behaviour
• Pensions and Pension Management
• Public and Nonprofit Management
• Strategic Management
• Supply Chain Management
• Browse content in Criminology and Criminal Justice
• Criminal Justice
• Criminology
• Forms of Crime
• International and Comparative Criminology
• Youth Violence and Juvenile Justice
• Development Studies
• Browse content in Economics
• Agricultural, Environmental, and Natural Resource Economics
• Asian Economics
• Behavioural Finance
• Behavioural Economics and Neuroeconomics
• Econometrics and Mathematical Economics
• Economic Systems
• Economic Methodology
• Economic History
• Economic Development and Growth
• Financial Markets
• Financial Institutions and Services
• General Economics and Teaching
• Health, Education, and Welfare
• History of Economic Thought
• International Economics
• Labour and Demographic Economics
• Law and Economics
• Macroeconomics and Monetary Economics
• Microeconomics
• Public Economics
• Urban, Rural, and Regional Economics
• Welfare Economics
• Browse content in Education
• Adult Education and Continuous Learning
• Care and Counselling of Students
• Early Childhood and Elementary Education
• Educational Equipment and Technology
• Educational Strategies and Policy
• Higher and Further Education
• Organization and Management of Education
• Philosophy and Theory of Education
• Schools Studies
• Secondary Education
• Teaching of a Specific Subject
• Teaching of Specific Groups and Special Educational Needs
• Teaching Skills and Techniques
• Browse content in Environment
• Applied Ecology (Social Science)
• Climate Change
• Conservation of the Environment (Social Science)
• Environmentalist Thought and Ideology (Social Science)
• Natural Disasters (Environment)
• Social Impact of Environmental Issues (Social Science)
• Browse content in Human Geography
• Cultural Geography
• Economic Geography
• Political Geography
• Browse content in Interdisciplinary Studies
• Communication Studies
• Museums, Libraries, and Information Sciences
• Browse content in Politics
• African Politics
• Asian Politics
• Chinese Politics
• Comparative Politics
• Conflict Politics
• Elections and Electoral Studies
• Environmental Politics
• European Union
• Foreign Policy
• Gender and Politics
• Human Rights and Politics
• Indian Politics
• International Relations
• International Organization (Politics)
• International Political Economy
• Irish Politics
• Latin American Politics
• Middle Eastern Politics
• Political Methodology
• Political Communication
• Political Philosophy
• Political Sociology
• Political Theory
• Political Behaviour
• Political Economy
• Political Institutions
• Politics and Law
• Public Administration
• Public Policy
• Quantitative Political Methodology
• Regional Political Studies
• Russian Politics
• Security Studies
• State and Local Government
• UK Politics
• US Politics
• Browse content in Regional and Area Studies
• African Studies
• Asian Studies
• East Asian Studies
• Japanese Studies
• Latin American Studies
• Middle Eastern Studies
• Native American Studies
• Scottish Studies
• Browse content in Research and Information
• Research Methods
• Browse content in Social Work
• Addictions and Substance Misuse
• Adoption and Fostering
• Care of the Elderly
• Child and Adolescent Social Work
• Couple and Family Social Work
• Developmental and Physical Disabilities Social Work
• Direct Practice and Clinical Social Work
• Emergency Services
• Human Behaviour and the Social Environment
• International and Global Issues in Social Work
• Mental and Behavioural Health
• Social Justice and Human Rights
• Social Policy and Advocacy
• Social Work and Crime and Justice
• Social Work Macro Practice
• Social Work Practice Settings
• Social Work Research and Evidence-based Practice
• Welfare and Benefit Systems
• Browse content in Sociology
• Childhood Studies
• Community Development
• Comparative and Historical Sociology
• Economic Sociology
• Gender and Sexuality
• Gerontology and Ageing
• Health, Illness, and Medicine
• Marriage and the Family
• Migration Studies
• Occupations, Professions, and Work
• Organizations
• Population and Demography
• Race and Ethnicity
• Social Theory
• Social Movements and Social Change
• Social Research and Statistics
• Social Stratification, Inequality, and Mobility
• Sociology of Religion
• Sociology of Education
• Sport and Leisure
• Urban and Rural Studies
• Browse content in Warfare and Defence
• Defence Strategy, Planning, and Research
• Land Forces and Warfare
• Military Administration
• Military Life and Institutions
• Naval Forces and Warfare
• Other Warfare and Defence Issues
• Peace Studies and Conflict Resolution
• Weapons and Equipment

• < Previous chapter
• Next chapter >

19 Content Analysis

Lindsay Prior, School of Sociology, Social Policy, and Social Work, Queen's University

• Published: 02 September 2020
• Cite Icon Cite
• Permissions Icon Permissions

In this chapter, the focus is on ways in which content analysis can be used to investigate and describe interview and textual data. The chapter opens with a contextualization of the method and then proceeds to an examination of the role of content analysis in relation to both quantitative and qualitative modes of social research. Following the introductory sections, four kinds of data are subjected to content analysis. These include data derived from a sample of qualitative interviews ( N = 54), textual data derived from a sample of health policy documents ( N = 6), data derived from a single interview relating to a “case” of traumatic brain injury, and data gathered from fifty-four abstracts of academic papers on the topic of “well-being.” Using a distinctive and somewhat novel style of content analysis that calls on the notion of semantic networks, the chapter shows how the method can be used either independently or in conjunction with other forms of inquiry (including various styles of discourse analysis) to analyze data and also how it can be used to verify and underpin claims that arise from analysis. The chapter ends with an overview of the different ways in which the study of “content”—especially the study of document content—can be positioned in social scientific research projects.

What Is Content Analysis?

In his 1952 text on the subject of content analysis, Bernard Berelson traced the origins of the method to communication research and then listed what he called six distinguishing features of the approach. As one might expect, the six defining features reflect the concerns of social science as taught in the 1950s, an age in which the calls for an “objective,” “systematic,” and “quantitative” approach to the study of communication data were first heard. The reference to the field of “communication” was nothing less than a reflection of a substantive social scientific interest over the previous decades in what was called public opinion and specifically attempts to understand why and how a potential source of critical, rational judgment on political leaders (i.e., the views of the public) could be turned into something to be manipulated by dictators and demagogues. In such a context, it is perhaps not so surprising that in one of the more popular research methods texts of the decade, the terms content analysis and communication analysis are used interchangeably (see Goode & Hatt, 1952 , p. 325).

Academic fashions and interests naturally change with available technology, and these days we are more likely to focus on the individualization of communications through Twitter and the like, rather than of mass newspaper readership or mass radio audiences, yet the prevailing discourse on content analysis has remained much the same as it was in Berleson’s day. Thus, Neuendorf ( 2002 ), for example, continued to define content analysis as “the systematic, objective, quantitative analysis of message characteristics” (p. 1). Clearly, the centrality of communication as a basis for understanding and using content analysis continues to hold, but in this chapter I will try to show that, rather than locate the use of content analysis in disembodied “messages” and distantiated “media,” we would do better to focus on the fact that communication is a building block of social life itself and not merely a system of messages that are transmitted—in whatever form—from sender to receiver. To put that statement in another guise, we must note that communicative action (to use the phraseology of Habermas, 1987 ) rests at the very base of the lifeworld, and one very important way of coming to grips with that world is to study the content of what people say and write in the course of their everyday lives.

My aim is to demonstrate various ways in which content analysis (henceforth CTA) can be used and developed to analyze social scientific data as derived from interviews and documents. It is not my intention to cover the history of CTA or to venture into forms of literary analysis or to demonstrate each and every technique that has ever been deployed by content analysts. (Many of the standard textbooks deal with those kinds of issues much more fully than is possible here. See, for example, Babbie, 2013 ; Berelson, 1952 ; Bryman, 2008 , Krippendorf, 2004 ; Neuendorf, 2002 ; and Weber, 1990 ). Instead, I seek to recontextualize the use of the method in a framework of network thinking and to link the use of CTA to specific problems of data analysis. As will become evident, my exposition of the method is grounded in real-world problems. Those problems are drawn from my own research projects and tend to reflect my academic interests—which are almost entirely related to the analysis of the ways in which people talk and write about aspects of health, illness, and disease. However, lest the reader be deterred from going any further, I should emphasize that the substantive issues that I elect to examine are secondary if not tertiary to my main objective—which is to demonstrate how CTA can be integrated into a range of research designs and add depth and rigor to the analysis of interview and inscription data. To that end, in the next section I aim to clear our path to analysis by dealing with some issues that touch on the general position of CTA in the research armory, especially its location in the schism that has developed between quantitative and qualitative modes of inquiry.

The Methodological Context of Content Analysis

Content analysis is usually associated with the study of inscription contained in published reports, newspapers, adverts, books, web pages, journals, and other forms of documentation. Hence, nearly all of Berelson’s ( 1952 ) illustrations and references to the method relate to the analysis of written records of some kind, and where speech is mentioned, it is almost always in the form of broadcast and published political speeches (such as State of the Union addresses). This association of content analysis with text and documentation is further underlined in modern textbook discussions of the method. Thus, Bryman ( 2008 ), for example, defined CTA as “an approach to the analysis of documents and texts , that seek to quantify content in terms of pre-determined categories” (2008, p. 274, emphasis in original), while Babbie ( 2013 ) stated that CTA is “the study of recorded human communications” (2013, p. 295), and Weber referred to it as a method to make “valid inferences from text” (1990, p. 9). It is clear then that CTA is viewed as a text-based method of analysis, though extensions of the method to other forms of inscriptional material are also referred to in some discussions. Thus, Neuendorf ( 2002 ), for example, rightly referred to analyses of film and television images as legitimate fields for the deployment of CTA and by implication analyses of still—as well as moving—images such as photographs and billboard adverts. Oddly, in the traditional or standard paradigm of CTA, the method is solely used to capture the “message” of a text or speech; it is not used for the analysis of a recipient’s response to or understanding of the message (which is normally accessed via interview data and analyzed in other and often less rigorous ways; see, e.g., Merton, 1968 ). So, in this chapter I suggest that we can take things at least one small step further by using CTA to analyze speech (especially interview data) as well as text.

Standard textbook discussions of CTA usually refer to it as a “nonreactive” or “unobtrusive” method of investigation (see, e.g., Babbie, 2013 , p. 294), and a large part of the reason for that designation is because of its focus on already existing text (i.e., text gathered without intrusion into a research setting). More important, however (and to underline the obvious), CTA is primarily a method of analysis rather than of data collection. Its use, therefore, must be integrated into wider frames of research design that embrace systematic forms of data collection as well as forms of data analysis. Thus, routine strategies for sampling data are often required in designs that call on CTA as a method of analysis. These latter can be built around random sampling methods or even techniques of “theoretical sampling” (Glaser & Strauss, 1967 ) so as to identify a suitable range of materials for CTA. Content analysis can also be linked to styles of ethnographic inquiry and to the use of various purposive or nonrandom sampling techniques. For an example, see Altheide ( 1987 ).

The use of CTA in a research design does not preclude the use of other forms of analysis in the same study, because it is a technique that can be deployed in parallel with other methods or with other methods sequentially. For example, and as I will demonstrate in the following sections, one might use CTA as a preliminary analytical strategy to get a grip on the available data before moving into specific forms of discourse analysis. In this respect, it can be as well to think of using CTA in, say, the frame of a priority/sequence model of research design as described by Morgan ( 1998 ).

As I shall explain, there is a sense in which CTA rests at the base of all forms of qualitative data analysis, yet the paradox is that the analysis of content is usually considered a quantitative (numerically based) method. In terms of the qualitative/quantitative divide, however, it is probably best to think of CTA as a hybrid method, and some writers have in the past argued that it is necessarily so (Kracauer, 1952 ). That was probably easier to do in an age when many recognized the strictly drawn boundaries between qualitative and quantitative styles of research to be inappropriate. Thus, in their widely used text Methods in Social Research , Goode and Hatt ( 1952 ), for example, asserted that “modern research must reject as a false dichotomy the separation between ‘qualitative’ and ‘quantitative’ studies, or between the ‘statistical’ and the ‘non-statistical’ approach” (p. 313). This position was advanced on the grounds that all good research must meet adequate standards of validity and reliability, whatever its style, and the message is well worth preserving. However, there is a more fundamental reason why it is nonsensical to draw a division between the qualitative and the quantitative. It is simply this: All acts of social observation depend on the deployment of qualitative categories—whether gender, class, race, or even age; there is no descriptive category in use in the social sciences that connects to a world of “natural kinds.” In short, all categories are made, and therefore when we seek to count “things” in the world, we are dependent on the existence of socially constructed divisions. How the categories take the shape that they do—how definitions are arrived at, how inclusion and exclusion criteria are decided on, and how taxonomic principles are deployed—constitute interesting research questions in themselves. From our starting point, however, we need only note that “sorting things out” (to use a phrase from Bowker & Star, 1999 ) and acts of “counting”—whether it be of chromosomes or people (Martin & Lynch, 2009 )—are activities that connect to the social world of organized interaction rather than to unsullied observation of the external world.

Some writers deny the strict division between the qualitative and quantitative on grounds of empirical practice rather than of ontological reasoning. For example, Bryman ( 2008 ) argued that qualitative researchers also call on quantitative thinking, but tend to use somewhat vague, imprecise terms rather than numbers and percentages—referring to frequencies via the use of phrases such as “more than” and “less than.” Kracauer ( 1952 ) advanced various arguments against the view that CTA was strictly a quantitative method, suggesting that very often we wished to assess content as being negative or positive with respect to some political, social, or economic thesis and that such evaluations could never be merely statistical. He further argued that we often wished to study “underlying” messages or latent content of documentation and that, in consequence, we needed to interpret content as well as count items of content. Morgan ( 1993 ) argued that, given the emphasis that is placed on “coding” in almost all forms of qualitative data analysis, the deployment of counting techniques is essential and we ought therefore to think in terms of what he calls qualitative as well as quantitative content analysis. Naturally, some of these positions create more problems than they seemingly solve (as is the case with considerations of “latent content”), but given the 21st-century predilection for mixed methods research (Creswell, 2007 ), it is clear that CTA has a role to play in integrating quantitative and qualitative modes of analysis in a systematic rather than merely ad hoc and piecemeal fashion. In the sections that follow, I will provide some examples of the ways in which “qualitative” analysis can be combined with systematic modes of counting. First, however, we must focus on what is analyzed in CTA.

Units of Analysis

So, what is the unit of analysis in CTA? A brief answer is that analysis can be focused on words, sentences, grammatical structures, tenses, clauses, ratios (of, say, nouns to verbs), or even “themes.” Berelson ( 1952 ) gave examples of all of the above and also recommended a form of thematic analysis (cf., Braun & Clarke, 2006 ) as a viable option. Other possibilities include counting column length (of speeches and newspaper articles), amounts of (advertising) space, or frequency of images. For our purposes, however, it might be useful to consider a specific (and somewhat traditional) example. Here it is. It is an extract from what has turned out to be one of the most important political speeches of the current century.

Iraq continues to flaunt its hostility toward America and to support terror. The Iraqi regime has plotted to develop anthrax and nerve gas and nuclear weapons for over a decade. This is a regime that has already used poison gas to murder thousands of its own citizens, leaving the bodies of mothers huddled over their dead children. This is a regime that agreed to international inspections then kicked out the inspectors. This is a regime that has something to hide from the civilized world. States like these, and their terrorist allies, constitute an axis of evil, arming to threaten the peace of the world. By seeking weapons of mass destruction, these regimes pose a grave and growing danger. They could provide these arms to terrorists, giving them the means to match their hatred. They could attack our allies or attempt to blackmail the United States. In any of these cases, the price of indifference would be catastrophic. (George W. Bush, State of the Union address, January 29, 2002)

A number of possibilities arise for analyzing the content of a speech such as the one above. Clearly, words and sentences must play a part in any such analysis, but in addition to words, there are structural features of the speech that could also figure. For example, the extract takes the form of a simple narrative—pointing to a past, a present, and an ominous future (catastrophe)—and could therefore be analyzed as such. There are, in addition, several interesting oppositions in the speech (such as those between “regimes” and the “civilized” world), as well as a set of interconnected present participles such as “plotting,” “hiding,” “arming,” and “threatening” that are associated both with Iraq and with other states that “constitute an axis of evil.” Evidently, simple word counts would fail to capture the intricacies of a speech of this kind. Indeed, our example serves another purpose—to highlight the difficulty that often arises in dissociating CTA from discourse analysis (of which narrative analysis and the analysis of rhetoric and trope are subspecies). So how might we deal with these problems?

One approach that can be adopted is to focus on what is referenced in text and speech, that is, to concentrate on the characters or elements that are recruited into the text and to examine the ways in which they are connected or co-associated. I shall provide some examples of this form of analysis shortly. Let us merely note for the time being that in the previous example we have a speech in which various “characters”—including weapons in general, specific weapons (such as nerve gas), threats, plots, hatred, evil, and mass destruction—play a role. Be aware that we need not be concerned with the veracity of what is being said—whether it is true or false—but simply with what is in the speech and how what is in there is associated. (We may leave the task of assessing truth and falsity to the jurists). Be equally aware that it is a text that is before us and not an insight into the ex-president’s mind, or his thinking, or his beliefs, or any other subjective property that he may have possessed.

In the introductory paragraph, I made brief reference to some ideas of the German philosopher Jürgen Habermas ( 1987 ). It is not my intention here to expand on the detailed twists and turns of his claims with respect to the role of language in the “lifeworld” at this point. However, I do intend to borrow what I regard as some particularly useful ideas from his work. The first is his claim—influenced by a strong line of 20th-century philosophical thinking—that language and culture are constitutive of the lifeworld (Habermas, 1987 , p. 125), and in that sense we might say that things (including individuals and societies) are made in language. That is a simple justification for focusing on what people say rather than what they “think” or “believe” or “feel” or “mean” (all of which have been suggested at one time or another as points of focus for social inquiry and especially qualitative forms of inquiry). Second, Habermas argued that speakers and therefore hearers (and, one might add, writers and therefore readers), in what he calls their speech acts, necessarily adopt a pragmatic relation to one of three worlds: entities in the objective world, things in the social world, and elements of a subjective world. In practice, Habermas ( 1987 , p. 120) suggested all three worlds are implicated in any speech act, but that there will be a predominant orientation to one of them. To rephrase this in a crude form, when speakers engage in communication, they refer to things and facts and observations relating to external nature, to aspects of interpersonal relations, and to aspects of private inner subjective worlds (thoughts, feelings, beliefs, etc.). One of the problems with locating CTA in “communication research” has been that the communications referred to are but a special and limited form of action (often what Habermas called strategic acts). In other words, television, newspaper, video, and Internet communications are just particular forms (with particular features) of action in general. Again, we might note in passing that the adoption of the Habermassian perspective on speech acts implies that much of qualitative analysis in particular has tended to focus only on one dimension of communicative action—the subjective and private. In this respect, I would argue that it is much better to look at speeches such as George W Bush’s 2002 State of the Union address as an “account” and to examine what has been recruited into the account, and how what has been recruited is connected or co-associated, rather than use the data to form insights into his (or his adviser’s) thoughts, feelings, and beliefs.

In the sections that follow, and with an emphasis on the ideas that I have just expounded, I intend to demonstrate how CTA can be deployed to advantage in almost all forms of inquiry that call on either interview (or speech-based) data or textual data. In my first example, I will show how CTA can be used to analyze a group of interviews. In the second example, I will show how it can be used to analyze a group of policy documents. In the third, I shall focus on a single interview (a “case”), and in the fourth and final example, I will show how CTA can be used to track the biography of a concept. In each instance, I shall briefly introduce the context of the “problem” on which the research was based, outline the methods of data collection, discuss how the data were analyzed and presented, and underline the ways in which CTA has sharpened the analytical strategy.

Analyzing a Sample of Interviews: Looking at Concepts and Their Co-associations in a Semantic Network

My first example of using CTA is based on a research study that was initially undertaken in the early 2000s. It was a project aimed at understanding why older people might reject the offer to be immunized against influenza (at no cost to them). The ultimate objective was to improve rates of immunization in the study area. The first phase of the research was based on interviews with 54 older people in South Wales. The sample included people who had never been immunized, some who had refused immunization, and some who had accepted immunization. Within each category, respondents were randomly selected from primary care physician patient lists, and the data were initially analyzed “thematically” and published accordingly (Evans, Prout, Prior, Tapper-Jones, & Butler, 2007 ). A few years later, however, I returned to the same data set to look at a different question—how (older) lay people talked about colds and flu, especially how they distinguished between the two illnesses and how they understood the causes of the two illnesses (see Prior, Evans, & Prout, 2011 ). Fortunately, in the original interview schedule, we had asked people about how they saw the “differences between cold and flu” and what caused flu, so it was possible to reanalyze the data with such questions in mind. In that frame, the example that follows demonstrates not only how CTA might be used on interview data, but also how it might be used to undertake a secondary analysis of a preexisting data set (Bryman, 2008 ).

As with all talk about illness, talk about colds and flu is routinely set within a mesh of concerns—about causes, symptoms, and consequences. Such talk comprises the base elements of what has at times been referred to as the “explanatory model” of an illness (Kleinman, Eisenberg, & Good, 1978 ). In what follows, I shall focus almost entirely on issues of causation as understood from the viewpoint of older people; the analysis is based on the answers that respondents made in response to the question, “How do you think people catch flu?”

Semistructured interviews of the kind undertaken for a study such as this are widely used and are often characterized as akin to “a conversation with a purpose” (Kahn & Cannell, 1957 , p. 97). One of the problems of analyzing the consequent data is that, although the interviewer holds to a planned schedule, the respondents often reflect in a somewhat unstructured way about the topic of investigation, so it is not always easy to unravel the web of talk about, say, “causes” that occurs in the interview data. In this example, causal agents of flu, inhibiting agents, and means of transmission were often conflated by the respondents. Nevertheless, in their talk people did answer the questions that were posed, and in the study referred to here, that talk made reference to things such as “bugs” (and “germs”) as well as viruses, but the most commonly referred to causes were “the air” and the “atmosphere.” The interview data also pointed toward means of transmission as “cause”—so coughs and sneezes and mixing in crowds figured in the causal mix. Most interesting, perhaps, was the fact that lay people made a nascent distinction between facilitating factors (such as bugs and viruses) and inhibiting factors (such as being resistant, immune, or healthy), so that in the presence of the latter, the former are seen to have very little effect. Here are some shorter examples of typical question–response pairs from the original interview data.

(R:32): “How do you catch it [the flu]? Well, I take it its through ingesting and inhaling bugs from the atmosphere. Not from sort of contact or touching things. Sort of airborne bugs. Is that right?” (R:3): “I suppose it’s [the cause of flu] in the air. I think I get more diseases going to the surgery than if I stayed home. Sometimes the waiting room is packed and you’ve got little kids coughing and spluttering and people sneezing, and air conditioning I think is a killer by and large I think air conditioning in lots of these offices.” (R:46): “I think you catch flu from other people. You know in enclosed environments in air conditioning which in my opinion is the biggest cause of transferring diseases is air conditioning. Worse thing that was ever invented that was. I think so, you know. It happens on aircraft exactly the same you know.”

Alternatively, it was clear that for some people being cold, wet, or damp could also serve as a direct cause of flu; thus: Interviewer: “OK, good. How do you think you catch the flu?”

(R:39): “Ah. The 65 dollar question. Well, I would catch it if I was out in the rain and I got soaked through. Then I would get the flu. I mean my neighbour up here was soaked through and he got pneumonia and he died. He was younger than me: well, 70. And he stayed in his wet clothes and that’s fatal. Got pneumonia and died, but like I said, if I get wet, especially if I get my head wet, then I can get a nasty head cold and it could develop into flu later.”

As I suggested earlier, despite the presence of bugs and germs, viruses, the air, and wetness or dampness, “catching” the flu is not a matter of simple exposure to causative agents. Thus, some people hypothesized that within each person there is a measure of immunity or resistance or healthiness that comes into play and that is capable of counteracting the effects of external agents. For example, being “hardened” to germs and harsh weather can prevent a person getting colds and flu. Being “healthy” can itself negate the effects of any causative agents, and healthiness is often linked to aspects of “good” nutrition and diet and not smoking cigarettes. These mitigating and inhibiting factors can either mollify the effects of infection or prevent a person “catching” the flu entirely. Thus, (R:45) argued that it was almost impossible for him to catch flu or cold “cos I got all this resistance.” Interestingly, respondents often used possessive pronouns in their discussion of immunity and resistance (“my immunity” and “my resistance”)—and tended to view them as personal assets (or capital) that might be compromised by mixing with crowds.

By implication, having a weak immune system can heighten the risk of contracting colds and flu and might therefore spur one to take preventive measures, such as accepting a flu shot. Some people believe that the flu shot can cause the flu and other illnesses. An example of what might be called lay “epidemiology” (Davison, Davey-Smith, & Frankel, 1991 ) is evident in the following extract.

(R:4): “Well, now it’s coincidental you know that [my brother] died after the jab, but another friend of mine, about 8 years ago, the same happened to her. She had the jab and about six months later, she died, so I know they’re both coincidental, but to me there’s a pattern.”

Normally, results from studies such as this are presented in exactly the same way as has just been set out. Thus, the researcher highlights given themes that are said to have emerged from the data and then provides appropriate extracts from the interviews to illustrate and substantiate the relevant themes. However, one reasonable question that any critic might ask about the selected data extracts concerns the extent to which they are “representative” of the material in the data set as a whole. Maybe, for example, the author has been unduly selective in his or her use of both themes and quotations. Perhaps, as a consequence, the author has ignored or left out talk that does not fit the arguments or extracts that might be considered dull and uninteresting compared to more exotic material. And these kinds of issues and problems are certainly common to the reporting of almost all forms of qualitative research. However, the adoption of CTA techniques can help to mollify such problems. This is so because, by using CTA, we can indicate the extent to which we have used all or just some of the data, and we can provide a view of the content of the entire sample of interviews rather than just the content and flavor of merely one or two interviews. In this light, we must consider Figure 19.1 , which is based on counting the number of references in the 54 interviews to the various “causes” of the flu, though references to the flu shot (i.e., inoculation) as a cause of flu have been ignored for the purpose of this discussion. The node sizes reflect the relative importance of each cause as determined by the concept count (frequency of occurrence). The links between nodes reflect the degree to which causes are co-associated in interview talk and are calculated according to a co-occurrence index (see, e.g., SPSS, 2007 , p. 183).

What causes flu? A lay perspective. Factors listed as causes of colds and flu in 54 interviews. Node size is proportional to number of references “as causes.” Line thickness is proportional to co-occurrence of any two “causes” in the set of interviews.

Given this representation, we can immediately assess the relative importance of the different causes as referred to in the interview data. Thus, we can see that such things as (poor) “hygiene” and “foreigners” were mentioned as a potential cause of flu—but mention of hygiene and foreigners was nowhere near as important as references to “the air” or to “crowds” or to “coughs and sneezes.” In addition, we can also determine the strength of the connections that interviewees made between one cause and another. Thus, there are relatively strong links between “resistance” and “coughs and sneezes,” for example.

In fact, Figure 19.1 divides causes into the “external” and the “internal,” or the facilitating and the impeding (lighter and darker nodes). Among the former I have placed such things as crowds, coughs, sneezes, and the air, while among the latter I have included “resistance,” “immunity,” and “health.” That division is a product of my conceptualizing and interpreting the data, but whichever way we organize the findings, it is evident that talk about the causes of flu belongs in a web or mesh of concerns that would be difficult to represent using individual interview extracts alone. Indeed, it would be impossible to demonstrate how the semantics of causation belong to a culture (rather than to individuals) in any other way. In addition, I would argue that the counting involved in the construction of the diagram functions as a kind of check on researcher interpretations and provides a source of visual support for claims that an author might make about, say, the relative importance of “damp” and “air” as perceived causes of disease. Finally, the use of CTA techniques allied with aspects of conceptualization and interpretation has enabled us to approach the interview data as a set and to consider the respondents as belonging to a community, rather than regarding them merely as isolated and disconnected individuals, each with their own views. It has also enabled us to squeeze some new findings out of old data, and I would argue that it has done so with advantage. There are other advantages to using CTA to explore data sets, which I will highlight in the next section.

Analyzing a Sample of Documents: Using Content Analysis to Verify Claims

Policy analysis is a difficult business. To begin, it is never entirely clear where (social, health, economic, environmental) policy actually is. Is it in documents (as published by governments, think tanks, and research centers), in action (what people actually do), or in speech (what people say)? Perhaps it rests in a mixture of all three realms. Yet, wherever it may be, it is always possible, at the very least, to identify a range of policy texts and to focus on the conceptual or semantic webs in terms of which government officials and other agents (such as politicians) talk about the relevant policy issues. Furthermore, insofar as policy is recorded—in speeches, pamphlets, and reports—we may begin to speak of specific policies as having a history or a pedigree that unfolds through time (think, e.g., of U.S. or U.K. health policies during the Clinton years or the Obama years). And, insofar as we consider “policy” as having a biography or a history, we can also think of studying policy narratives.

Though firmly based in the world of literary theory, narrative method has been widely used for both the collection and the analysis of data concerning ways in which individuals come to perceive and understand various states of health, ill health, and disability (Frank, 1995 ; Hydén, 1997 ). Narrative techniques have also been adapted for use in clinical contexts and allied to concepts of healing (Charon, 2006 ). In both social scientific and clinical work, however, the focus is invariably on individuals and on how individuals “tell” stories of health and illness. Yet narratives can also belong to collectives—such as political parties and ethnic and religious groups—just as much as to individuals, and in the latter case there is a need to collect and analyze data that are dispersed across a much wider range of materials than can be obtained from the personal interview. In this context, Roe ( 1994 ) demonstrated how narrative method can be applied to an analysis of national budgets, animal rights, and environmental policies.

An extension of the concept of narrative to policy discourse is undoubtedly useful (Newman & Vidler, 2006 ), but how might such narratives be analyzed? What strategies can be used to unravel the form and content of a narrative, especially in circumstances where the narrative might be contained in multiple (policy) documents, authored by numerous individuals, and published across a span of time rather than in a single, unified text such as a novel? Roe ( 1994 ), unfortunately, was not in any way specific about analytical procedures, apart from offering the useful rule to “never stray too far from the data” (p. xii). So, in this example, I will outline a strategy for tackling such complexities. In essence, it is a strategy that combines techniques of linguistically (rule) based CTA with a theoretical and conceptual frame that enables us to unravel and identify the core features of a policy narrative. My substantive focus is on documents concerning health service delivery policies published from 2000 to 2009 in the constituent countries of the United Kingdom (that is, England, Scotland, Wales, and Northern Ireland—all of which have different political administrations).

Narratives can be described and analyzed in various ways, but for our purposes we can say that they have three key features: they point to a chronology, they have a plot, and they contain “characters.”

All narratives have beginnings; they also have middles and endings, and these three stages are often seen as comprising the fundamental structure of narrative text. Indeed, in his masterly analysis of time and narrative, Ricoeur ( 1984 ) argued that it is in the unfolding chronological structure of a narrative that one finds its explanatory (and not merely descriptive) force. By implication, one of the simplest strategies for the examination of policy narratives is to locate and then divide a narrative into its three constituent parts—beginning, middle, and end.

Unfortunately, while it can sometimes be relatively easy to locate or choose a beginning to a narrative, it can be much more difficult to locate an end point. Thus, in any illness narrative, a narrator might be quite capable of locating the start of an illness process (in an infection, accident, or other event) but unable to see how events will be resolved in an ongoing and constantly unfolding life. As a consequence, both narrators and researchers usually find themselves in the midst of an emergent present—a present without a known and determinate end (see, e.g., Frank, 1995 ). Similar considerations arise in the study of policy narratives where chronology is perhaps best approached in terms of (past) beginnings, (present) middles, and projected futures.

According to Ricoeur ( 1984 ), our basic ideas about narrative are best derived from the work and thought of Aristotle, who in his Poetics sought to establish “first principles” of composition. For Ricoeur, as for Aristotle, plot ties things together. It “brings together factors as heterogeneous as agents, goals, means, interactions, circumstances, unexpected results” (p. 65) into the narrative frame. For Aristotle, it is the ultimate untying or unraveling of the plot that releases the dramatic energy of the narrative.

Characters are most commonly thought of as individuals, but they can be considered in much broader terms. Thus, the French semiotician A. J. Greimas ( 1970 ), for example, suggested that, rather than think of characters as people, it would be better to think in terms of what he called actants and of the functions that such actants fulfill within a story. In this sense, geography, climate, and capitalism can be considered characters every bit as much as aggressive wolves and Little Red Riding Hood. Further, he argued that the same character (actant) can be considered to fulfill many functions, and the same function may be performed by many characters. Whatever else, the deployment of the term actant certainly helps us to think in terms of narratives as functioning and creative structures. It also serves to widen our understanding of the ways in which concepts, ideas, and institutions, as well “things” in the material world, can influence the direction of unfolding events every bit as much as conscious human subjects. Thus, for example, the “American people,” “the nation,” “the Constitution,” “the West,” “tradition,” and “Washington” can all serve as characters in a policy story.

As I have already suggested, narratives can unfold across many media and in numerous arenas—speech and action, as well as text. Here, however, my focus is solely on official documents—all of which are U.K. government policy statements, as listed in Table 19.1 . The question is, How might CTA help us unravel the narrative frame?

It might be argued that a simple reading of any document should familiarize the researcher with elements of all three policy narrative components (plot, chronology, and character). However, in most policy research, we are rarely concerned with a single and unified text, as is the case with a novel; rather, we have multiple documents written at distinctly different times by multiple (usually anonymous) authors that notionally can range over a wide variety of issues and themes. In the full study, some 19 separate publications were analyzed across England, Wales, Scotland, and Northern Ireland.

Naturally, listing word frequencies—still less identifying co-occurrences and semantic webs in large data sets (covering hundreds of thousands of words and footnotes)—cannot be done manually, but rather requires the deployment of complex algorithms and text-mining procedures. To this end, I analyzed the 19 documents using “Text Mining for Clementine” (SPSS, 2007 ).

Text-mining procedures begin by providing an initial list of concepts based on the lexicon of the text but that can be weighted according to word frequency and that take account of elementary word associations. For example, learning disability, mental health, and performance management indicate three concepts, not six words. Using such procedures on the aforementioned documents gives the researcher an initial grip on the most important concepts in the document set of each country. Note that this is much more than a straightforward concordance analysis of the text and is more akin to what Ryan and Bernard ( 2000 ) referred to as semantic analysis and Carley ( 1993 ) has referred to as concept and mapping analysis.

So, the first task was to identify and then extract the core concepts, thus identifying what might be called “key” characters or actants in each of the policy narratives. For example, in the Scottish documents, such actants included “Scotland” and the “Scottish people,” as well as “health” and the “National Health Service (NHS),” among others, while in the Welsh documents it was “the people of Wales” and “Wales” that figured largely—thus emphasizing how national identity can play every bit as important a role in a health policy narrative as concepts such as “health,” “hospitals,” and “well-being.”

Having identified key concepts, it was then possible to track concept clusters in which particular actants or characters are embedded. Such cluster analysis is dependent on the use of co-occurrence rules and the analysis of synonyms, whereby it is possible to get a grip on the strength of the relationships between the concepts, as well as the frequency with which the concepts appear in the collected texts. In Figure 19.2 , I provide an example of a concept cluster. The diagram indicates the nature of the conceptual and semantic web in which various actants are discussed. The diagrams further indicate strong (solid line) and weaker (dashed line) connections between the various elements in any specific mix, and the numbers indicate frequency counts for the individual concepts. Using Clementine , the researcher is unable to specify in advance which clusters will emerge from the data. One cannot, for example, choose to have an NHS cluster. In that respect, these diagrams not only provide an array in terms of which concepts are located, but also serve as a check on and to some extent validation of the interpretations of the researcher. None of this tells us what the various narratives contained within the documents might be, however. They merely point to key characters and relationships both within and between the different narratives. So, having indicated the techniques used to identify the essential parts of the four policy narratives, it is now time to sketch out their substantive form.

Concept cluster for “care” in six English policy documents, 2000–2007. Line thickness is proportional to the strength co-occurrence coefficient. Node size reflects relative frequency of concept, and (numbers) refer to the frequency of concept. Solid lines indicate relationships between terms within the same cluster, and dashed lines indicate relationships between terms in different clusters.

It may be useful to note that Aristotle recommended brevity in matters of narrative—deftly summarizing the whole of the Odyssey in just seven lines. In what follows, I attempt—albeit somewhat weakly—to emulate that example by summarizing a key narrative of English health services policy in just four paragraphs. Note how the narrative unfolds in relation to the dates of publication. In the English case (though not so much in the other U.K. countries), it is a narrative that is concerned to introduce market forces into what is and has been a state-managed health service. Market forces are justified in terms of improving opportunities for the consumer (i.e., the patients in the service), and the pivot of the newly envisaged system is something called “patient choice” or “choice.” This is how the story unfolds as told through the policy documents between 2000 and 2008 (see Table 19.1 ). The citations in the following paragraphs are to the Department of Health publications (by year) listed in Table 19.1 .

The advent of the NHS in 1948 was a “seminal event” (2000, p. 8), but under successive Conservative administrations, the NHS was seriously underfunded (2006, p. 3). The (New Labour) government will invest (2000) or already has (2003, p. 4) invested extensively in infrastructure and staff, and the NHS is now on a “journey of major improvement” (2004, p. 2). But “more money is only a starting point” (2000, p. 2), and the journey is far from finished. Continuation requires some fundamental changes of “culture” (2003, p. 6). In particular, the NHS remains unresponsive to patient need, and “all too often, the individual needs and wishes are secondary to the convenience of the services that are available. This ‘one size fits all’ approach is neither responsive, equitable nor person-centred” (2003, p. 17). In short, the NHS is a 1940s system operating in a 21st-century world (2000, p. 26). Change is therefore needed across the “whole system” (2005, p. 3) of care and treatment.

Above all, we must recognize that we “live in a consumer age” (2000, p. 26). People’s expectations have changed dramatically (2006, p. 129), and people want more choice, more independence, and more control (2003, p. 12) over their affairs. Patients are no longer, and should not be considered, “passive recipients” of care (2003, p. 62), but wish to be and should be (2006, p. 81) actively “involved” in their treatments (2003, p. 38; 2005, p. 18)—indeed, engaged in a partnership (2003, p. 22) of respect with their clinicians. Furthermore, most people want a personalized service “tailor made to their individual needs” (2000, p. 17; 2003, p. 15; 2004, p. 1; 2006, p. 83)—“a service which feels personal to each and every individual within a framework of equity and good use of public money” (2003, p. 6).

To advance the necessary changes, “patient choice” must be and “will be strengthened” (2000, p. 89). “Choice” must be made to “happen” (2003), and it must be “real” (2003, p. 3; 2004, p. 5; 2005, p. 20; 2006, p. 4). Indeed, it must be “underpinned” (2003, p. 7) and “widened and deepened” (2003, p. 6) throughout the entire system of care.

If “we” expand and underpin patient choice in appropriate ways and engage patients in their treatment systems, then levels of patient satisfaction will increase (2003, p. 39), and their choices will lead to a more “efficient” (2003, p. 5; 2004, p. 2; 2006, p. 16) and effective (2003, p. 62; 2005, p. 8) use of resources. Above all, the promotion of choice will help to drive up “standards” of care and treatment (2000, p. 4; 2003, p. 12; 2004, p. 3; 2005, p. 7; 2006, p. 3). Furthermore, the expansion of choice will serve to negate the effects of the “inverse care law,” whereby those who need services most tend to get catered to the least (2000, p. 107; 2003, p. 5; 2006, p. 63), and it will thereby help in moderating the extent of health inequalities in the society in which we live. “The overall aim of all our reforms,” therefore, “is to turn the NHS from a top down monolith into a responsive service that gives the patient the best possible experience. We need to develop an NHS that is both fair to all of us, and personal to each of us” (2003, p. 5).

We can see how most—though not all—of the elements of this story are represented in Figure 19.2. In particular, we can see strong (co-occurrence) links between care and choice and how partnership, performance, control, and improvement have a prominent profile. There are some elements of the web that have a strong profile (in terms of node size and links), but to which we have not referred; access, information, primary care, and waiting times are four. As anyone well versed in English healthcare policy would know, these elements have important roles to play in the wider, consumer-driven narrative. However, by rendering the excluded as well as included elements of that wider narrative visible, the concept web provides a degree of verification on the content of the policy story as told herein and on the scope of its “coverage.”

In following through on this example, we have moved from CTA to a form of discourse analysis (in this instance, narrative analysis). That shift underlines aspects of both the versatility of CTA and some of its weaknesses—versatility in the sense that CTA can be readily combined with other methods of analysis and in the way in which the results of the CTA help us to check and verify the claims of the researcher. The weakness of the diagram compared to the narrative is that CTA on its own is a somewhat one-dimensional and static form of analysis, and while it is possible to introduce time and chronology into the diagrams, the diagrams themselves remain lifeless in the absence of some form of discursive overview. (For a fuller analysis of these data, see Prior, Hughes, & Peckham, 2012 ).

Analyzing a Single Interview: The Role of Content Analysis in a Case Study

So far, I have focused on using CTA on a sample of interviews and a sample of documents. In the first instance, I recommended CTA for its capacity to tell us something about what is seemingly central to interviewees and for demonstrating how what is said is linked (in terms of a concept network). In the second instance, I reaffirmed the virtues of co-occurrence and network relations, but this time in the context of a form of discourse analysis. I also suggested that CTA can serve an important role in the process of verification of a narrative and its academic interpretation. In this section, however, I am going to link the use of CTA to another style of research—case study—to show how CTA might be used to analyze a single “case.”

Case study is a term used in multiple and often ambiguous ways. However, Gerring ( 2004 ) defined it as “an intensive study of a single unit for the purpose of understanding a larger class of (similar) units” (p. 342). As Gerring pointed out, case study does not necessarily imply a focus on N = 1, although that is indeed the most logical number for case study research (Ragin & Becker, 1992 ). Naturally, an N of 1 can be immensely informative, and whether we like it or not, we often have only one N to study (think, e.g., of the 1986 Challenger shuttle disaster or of the 9/11 attack on the World Trade Center). In the clinical sciences, case studies are widely used to represent the “typical” features of a wider class of phenomena and often used to define a kind or syndrome (as in the field of clinical genetics). Indeed, at the risk of mouthing a tautology, one can say that the distinctive feature of case study is its focus on a case in all of its complexity—rather than on individual variables and their interrelationships, which tends to be a point of focus for large N research.

There was a time when case study was central to the science of psychology. Breuer and Freud’s (2001) famous studies of “hysteria” (originally published in 1895) provide an early and outstanding example of the genre in this respect, but as with many of the other styles of social science research, the influence of case studies waned with the rise of much more powerful investigative techniques—including experimental methods—driven by the deployment of new statistical technologies. Ideographic studies consequently gave way to the current fashion for statistically driven forms of analysis that focus on causes and cross-sectional associations between variables rather than ideographic complexity.

In the example that follows, we will look at the consequences of a traumatic brain injury (TBI) on just one individual. The analysis is based on an interview with a person suffering from such an injury, and it was one of 32 interviews carried out with people who had experienced a TBI. The objective of the original research was to develop an outcome measure for TBI that was sensitive to the sufferer’s (rather than the health professional’s) point of view. In our original study (see Morris et al., 2005 ), interviews were also undertaken with 27 carers of the injured with the intention of comparing their perceptions of TBI to those of the people for whom they cared. A sample survey was also undertaken to elicit views about TBI from a much wider population of patients than was studied via interview.

In the introduction, I referred to Habermas and the concept of the lifeworld. Lifeworld ( Lebenswelt ) is a concept that first arose from 20th-century German philosophy. It constituted a specific focus for the work of Alfred Schutz (see, e.g., Schutz & Luckman, 1974 ). Schutz ( 1974 ) described the lifeworld as “that province of reality which the wide-awake and normal adult simply takes-for-granted in an attitude of common sense” (p. 3). Indeed, it was the routine and taken-for-granted quality of such a world that fascinated Schutz. As applied to the worlds of those with head injuries, the concept has particular resonance because head injuries often result in that taken-for-granted quality being disrupted and fragmented, ending in what Russian neuropsychologist A. R. Luria ( 1975 ) once described as “shattered” worlds. As well as providing another excellent example of a case study, Luria’s work is also pertinent because he sometimes argued for a “romantic science” of brain injury—that is, a science that sought to grasp the worldview of the injured patient by paying attention to an unfolding and detailed personal “story” of the individual with the head injury as well as to the neurological changes and deficits associated with the injury itself. In what follows, I shall attempt to demonstrate how CTA might be used to underpin such an approach.

In the original research, we began analysis by a straightforward reading of the interview transcripts. Unfortunately, a simple reading of a text or an interview can, strangely, mislead the reader into thinking that some issues or themes are more important than is warranted by the contents of the text. How that comes about is not always clear, but it probably has something to do with a desire to develop “findings” and our natural capacity to overlook the familiar in favor of the unusual. For that reason alone, it is always useful to subject any text to some kind of concordance analysis—that is, generating a simple frequency list of words used in an interview or text. Given the current state of technology, one might even speak these days of using text-mining procedures such as the aforementioned Clementine to undertake such a task. By using Clementine , and as we have seen, it is also possible to measure the strength of co-occurrence links between elements (i.e., words and concepts) in the entire data set (in this example, 32 interviews), though for a single interview these aims can just as easily be achieved using much simpler, low-tech strategies.

By putting all 32 interviews into the database, several common themes emerged. For example, it was clear that “time” entered into the semantic web in a prominent manner, and it was clearly linked to such things as “change,” “injury,” “the body,” and what can only be called the “I was.” Indeed, time runs through the 32 stories in many guises, and the centrality of time is a reflection of storytelling and narrative recounting in general—chronology, as we have noted, being a defining feature of all storytelling (Ricoeur, 1984 ). Thus, sufferers both recounted the events surrounding their injury and provided accounts as to how the injuries affected their current life and future hopes. As to time present, much of the patient story circled around activities of daily living—walking, working, talking, looking, feeling, remembering, and so forth.

Understandably, the word and the concept of “injury” featured largely in the interviews, though it was a word most commonly associated with discussions of physical consequences of injury. There were many references in that respect to injured arms, legs, hands, and eyes. There were also references to “mind”—though with far less frequency than with references to the body and to body parts. Perhaps none of this is surprising. However, one of the most frequent concepts in the semantic mix was the “I was” (716 references). The statement “I was,” or “I used to” was, in turn, strongly connected to terms such as “the accident” and “change.” Interestingly, the “I was” overwhelmingly eclipsed the “I am” in the interview data (the latter with just 63 references). This focus on the “I was” appears in many guises. For example, it is often associated with the use of the passive voice: “I was struck by a car,” “I was put on the toilet,” “I was shipped from there then, transferred to [Cityville],” “I got told that I would never be able …,” “I was sat in a room,” and so forth. In short, the “I was” is often associated with things, people, and events acting on the injured person. More important, however, the appearance of the “I was” is often used to preface statements signifying a state of loss or change in the person’s course of life—that is, as an indicator for talk about the patient’s shattered world. For example, Patient 7122 stated,

The main (effect) at the moment is I’m not actually with my children, I can’t really be their mum at the moment. I was a caring Mum, but I can’t sort of do the things that I want to be able to do like take them to school. I can’t really do a lot on my own. Like crossing the roads.

Another patient stated,

Everything is completely changed. The way I was … I can’t really do anything at the moment. I mean my German, my English, everything’s gone. Job possibilities is out the window. Everything is just out of the window … I just think about it all the time actually every day you know. You know it has destroyed me anyway, but if I really think about what has happened I would just destroy myself.

Each of these quotations, in its own way, serves to emphasize how life has changed and how the patient’s world has changed. In that respect, we can say that one of the major outcomes arising from TBI may be substantial “biographical disruption” (Bury, 1982 ), whereupon key features of an individual’s life course are radically altered forever. Indeed, as Becker ( 1997 , p. 37) argued in relation to a wide array of life events, “When their health is suddenly disrupted, people are thrown into chaos. Illness challenges one’s knowledge of one’s body. It defies orderliness. People experience the time before their illness and its aftermath as two separate entities.” Indeed, this notion of a cusp in personal biography is particularly well illustrated by Luria’s patient Zasetsky; the latter often refers to being a “newborn creature” (Luria, 1975 , pp. 24, 88), a shadow of a former self (p. 25), and as having his past “wiped out” (p. 116).

However, none of this tells us about how these factors come together in the life and experience of one individual. When we focus on an entire set of interviews, we necessarily lose the rich detail of personal experience and tend instead to rely on a conceptual rather than a graphic description of effects and consequences (to focus on, say, “memory loss,” rather than loss of memory about family life). The contents of Figure 19.3 attempt to correct that vision. Figure 19.3 records all the things that a particular respondent (Patient 7011) used to do and liked doing. It records all the things that he says he can no longer do (at 1 year after injury), and it records all the consequences that he suffered from his head injury at the time of the interview. Thus, we see references to epilepsy (his “fits”), paranoia (the patient spoke of his suspicions concerning other people, people scheming behind his back, and his inability to trust others), deafness, depression, and so forth. Note that, although I have inserted a future tense into the web (“I will”), such a statement never appeared in the transcript. I have set it there for emphasis and to show how, for this person, the future fails to connect to any of the other features of his world except in a negative way. Thus, he states at one point that he cannot think of the future because it makes him feel depressed (see Figure 19.3 ). The line thickness of the arcs reflects the emphasis that the subject placed on the relevant “outcomes” in relation to the “I was” and the “now” during the interview. Thus, we see that factors affecting his concentration and balance loom large, but that he is also concerned about his being dependent on others, his epileptic fits, and his being unable to work and drive a vehicle. The schism in his life between what he used to do, what he cannot now do, and his current state of being is nicely represented in the CTA diagram.

The shattered world of Patient 7011. Thickness of lines (arcs) is proportional to the frequency of reference to the “outcome” by the patient during the interview.

What have we gained from executing this kind of analysis? For a start, we have moved away from a focus on variables, frequencies, and causal connections (e.g., a focus on the proportion of people with TBI who suffer from memory problems or memory problems and speech problems) and refocused on how the multiple consequences of a TBI link together in one person. In short, instead of developing a narrative of acting variables, we have emphasized a narrative of an acting individual (Abbott, 1992 , p. 62). Second, it has enabled us to see how the consequences of a TBI connect to an actual lifeworld (and not simply an injured body). So the patient is not viewed just as having a series of discrete problems such as balancing, or staying awake, which is the usual way of assessing outcomes, but as someone struggling to come to terms with an objective world of changed things, people, and activities (missing work is not, for example, routinely considered an outcome of head injury). Third, by focusing on what the patient was saying, we gain insight into something that is simply not visible by concentrating on single outcomes or symptoms alone—namely, the void that rests at the center of the interview, what I have called the “I was.” Fourth, we have contributed to understanding a type, because the case that we have read about is not simply a case of “John” or “Jane” but a case of TBI, and in that respect it can add to many other accounts of what it is like to experience head injury—including one of the most well documented of all TBI cases, that of Zatetsky. Finally, we have opened up the possibility of developing and comparing cognitive maps (Carley, 1993 ) for different individuals and thereby gained insight into how alternative cognitive frames of the world arise and operate.

Tracing the Biography of a Concept

In the previous sections, I emphasized the virtues of CTA for its capacity to link into a data set in its entirety—and how the use of CTA can counter any tendency of a researcher to be selective and partial in the presentation and interpretation of information contained in interviews and documents. However, that does not mean that we always must take an entire document or interview as the data source. Indeed, it is possible to select (on rational and explicit grounds) sections of documentation and to conduct the CTA on the chosen portions. In the example that follows, I do just that. The sections that I chose to concentrate on are titles and abstracts of academic papers—rather than the full texts. The research on which the following is based is concerned with a biography of a concept and is being conducted in conjunction with a Ph.D. student of mine, Joanne Wilson. Joanne thinks of this component of the study more in terms of a “scoping study” than of a biographical study, and that, too, is a useful framework for structuring the context in which CTA can be used. Scoping studies (Arksey & O’Malley, 2005 ) are increasingly used in health-related research to “map the field” and to get a sense of the range of work that has been conducted on a given topic. Such studies can also be used to refine research questions and research designs. In our investigation, the scoping study was centered on the concept of well-being. Since 2010, well-being has emerged as an important research target for governments and corporations as well as for academics, yet it is far from clear to what the term refers. Given the ambiguity of meaning, it is clear that a scoping review, rather than either a systematic review or a narrative review of available literature, would be best suited to our goals.

The origins of the concept of well-being can be traced at least as far back as the 4th century bc , when philosophers produced normative explanations of the good life (e.g., eudaimonia, hedonia, and harmony). However, contemporary interest in the concept seemed to have been regenerated by the concerns of economists and, most recently, psychologists. These days, governments are equally concerned with measuring well-being to inform policy and conduct surveys of well-being to assess that state of the nation (see, e.g., Office for National Statistics, 2012 )—but what are they assessing?

We adopted a two-step process to address the research question, “What is the meaning of ‘well-being’ in the context of public policy?” First, we explored the existing thesauri of eight databases to establish those higher order headings (if any) under which articles with relevance to well-being might be cataloged. Thus, we searched the following databases: Cumulative Index of Nursing and Allied Health Literature, EconLit, Health Management Information Consortium, Medline, Philosopher’s Index, PsycINFO, Sociological Abstracts, and Worldwide Political Science Abstracts. Each of these databases adopts keyword-controlled vocabularies. In other words, they use inbuilt statistical procedures to link core terms to a set lexis of phrases that depict the concepts contained in the database. Table 19.2 shows each database and its associated taxonomy. The contents of Table 19.2 point toward a linguistic infrastructure in terms of which academic discourse is conducted, and our task was to extract from this infrastructure the semantic web wherein the concept of well-being is situated. We limited the thesaurus terms to well-being and its variants (i.e., wellbeing or well being). If the term was returned, it was then exploded to identify any associated terms.

To develop the conceptual map, we conducted a free-text search for well-being and its variants within the context of public policy across the same databases. We orchestrated these searches across five time frames: January 1990 to December 1994, January 1995 to December 1999, January 2000 to December 2004, January 2005 to December 2009, and January 2010 to October 2011. Naturally, different disciplines use different words to refer to well-being, each of which may wax and wane in usage over time. The searches thus sought to quantitatively capture any changes in the use and subsequent prevalence of well-being and any referenced terms (i.e., to trace a biography).

It is important to note that we did not intend to provide an exhaustive, systematic search of all the relevant literature. Rather, we wanted to establish the prevalence of well-being and any referenced (i.e., allied) terms within the context of public policy. This has the advantage of ensuring that any identified words are grounded in the literature (i.e., they represent words actually used by researchers to talk and write about well-being in policy settings). The searches were limited to abstracts to increase the specificity, albeit at some expense to sensitivity, with which we could identify relevant articles.

We also employed inclusion/exclusion criteria to facilitate the process by which we selected articles, thereby minimizing any potential bias arising from our subjective interpretations. We included independent, stand-alone investigations relevant to the study’s objectives (i.e., concerned with well-being in the context of public policy), which focused on well-being as a central outcome or process and which made explicit reference to “well-being” and “public policy” in either the title or the abstract. We excluded articles that were irrelevant to the study’s objectives, those that used noun adjuncts to focus on the well-being of specific populations (i.e., children, elderly, women) and contexts (e.g., retirement village), and those that focused on deprivation or poverty unless poverty indices were used to understand well-being as opposed to social exclusion. We also excluded book reviews and abstracts describing a compendium of studies.

Using these criteria, Joanne Wilson conducted the review and recorded the results on a template developed specifically for the project, organized chronologically across each database and timeframe. Results were scrutinized by two other colleagues to ensure the validity of the search strategy and the findings. Any concerns regarding the eligibility of studies for inclusion were discussed among the research team. I then analyzed the co-occurrence of the key terms in the database. The resultant conceptual map is shown in Figure 19.4.

The position of a concept in a network—a study of “well-being.” Node size is proportional to the frequency of terms in 54 selected abstracts. Line thickness is proportional to the co-occurrence of two terms in any phrase of three words (e.g., subjective well-being, economics of well-being, well-being and development).

The diagram can be interpreted as a visualization of a conceptual space. So, when academics write about well-being in the context of public policy, they tend to connect the discussion to the other terms in the matrix. “Happiness,” “health,” “economic,” and “subjective,” for example, are relatively dominant terms in the matrix. The node size of these words suggests that references to such entities is only slightly less than references to well-being itself. However, when we come to analyze how well-being is talked about in detail, we see specific connections come to the fore. Thus, the data imply that talk of “subjective well-being” far outweighs discussion of “social well-being” or “economic well-being.” Happiness tends to act as an independent node (there is only one occurrence of happiness and well-being), probably suggesting that “happiness” is acting as a synonym for well-being. Quality of life is poorly represented in the abstracts, and its connection to most of the other concepts in the space is very weak—confirming, perhaps, that quality of life is unrelated to contemporary discussions of well-being and happiness. The existence of “measures” points to a distinct concern to assess and to quantify expressions of happiness, well-being, economic growth, and gross domestic product. More important and underlying this detail, there are grounds for suggesting that there are in fact a number of tensions in the literature on well-being.

On the one hand, the results point toward an understanding of well-being as a property of individuals—as something that they feel or experience. Such a discourse is reflected through the use of words like happiness, subjective , and individual . This individualistic and subjective frame has grown in influence over the past decade in particular, and one of the problems with it is that it tends toward a somewhat content-free conceptualization of well-being. To feel a sense of well-being, one merely states that one is in a state of well-being; to be happy, one merely proclaims that one is happy (cf., Office for National Statistics, 2012 ). It is reminiscent of the conditions portrayed in Aldous Huxley’s Brave New World , wherein the rulers of a closely managed society gave their priority to maintaining order and ensuring the happiness of the greatest number—in the absence of attention to justice or freedom of thought or any sense of duty and obligation to others, many of whom were systematically bred in “the hatchery” as slaves.

On the other hand, there is some intimation in our web that the notion of well-being cannot be captured entirely by reference to individuals alone and that there are other dimensions to the concept—that well-being is the outcome or product of, say, access to reasonable incomes, to safe environments, to “development,” and to health and welfare. It is a vision hinted at by the inclusion of those very terms in the network. These different concepts necessarily give rise to important differences concerning how well-being is identified and measured and therefore what policies are most likely to advance well-being. In the first kind of conceptualization, we might improve well-being merely by dispensing what Huxley referred to as “soma” (a superdrug that ensured feelings of happiness and elation); in the other case, however, we would need to invest in economic, human, and social capital as the infrastructure for well-being. In any event and even at this nascent level, we can see how CTA can begin to tease out conceptual complexities and theoretical positions in what is otherwise routine textual data.

Putting the Content of Documents in Their Place

I suggested in my introduction that CTA was a method of analysis—not a method of data collection or a form of research design. As such, it does not necessarily inveigle us into any specific forms of either design or data collection, though designs and methods that rely on quantification are dominant. In this closing section, however, I want to raise the issue as to how we should position a study of content in our research strategies as a whole. We must keep in mind that documents and records always exist in a context and that while what is “in” the document may be considered central, a good research plan can often encompass a variety of ways of looking at how content links to context. Hence, in what follows, I intend to outline how an analysis of content might be combined with other ways of looking at a record or text and even how the analysis of content might be positioned as secondary to an examination of a document or record. The discussion calls on a much broader analysis, as presented in Prior ( 2011 ).

I have already stated that basic forms of CTA can serve as an important point of departure for many types of data analysis—for example, as discourse analysis. Naturally, whenever “discourse” is invoked, there is at least some recognition of the notion that words might play a part in structuring the world rather than merely reporting on it or describing it (as is the case with the 2002 State of the Nation address that was quoted in the section “Units of Analysis”). Thus, for example, there is a considerable tradition within social studies of science and technology for examining the place of scientific rhetoric in structuring notions of “nature” and the position of human beings (especially as scientists) within nature (see, e.g., work by Bazerman, 1988 ; Gilbert & Mulkay, 1984 ; and Kay, 2000 ). Nevertheless, little, if any, of that scholarship situates documents as anything other than inert objects, either constructed by or waiting patiently to be activated by scientists.

However, in the tradition of the ethnomethodologists (Heritage, 1991 ) and some adherents of discourse analysis, it is also possible to argue that documents might be more fruitfully approached as a “topic” (Zimmerman & Pollner, 1971 ) rather than a “resource” (to be scanned for content), in which case the focus would be on the ways in which any given document came to assume its present content and structure. In the field of documentation, these latter approaches are akin to what Foucault ( 1970 ) might have called an “archaeology of documentation” and are well represented in studies of such things as how crime, suicide, and other statistics and associated official reports and policy documents are routinely generated. That, too, is a legitimate point of research focus, and it can often be worth examining the genesis of, say, suicide statistics or statistics about the prevalence of mental disorder in a community as well as using such statistics as a basis for statistical modeling.

Unfortunately, the distinction between topic and resource is not always easy to maintain—especially in the hurly-burly of doing empirical research (see, e.g., Prior, 2003 ). Putting an emphasis on “topic,” however, can open a further dimension of research that concerns the ways in which documents function in the everyday world. And, as I have already hinted, when we focus on function, it becomes apparent that documents serve not merely as containers of content but also very often as active agents in episodes of interaction and schemes of social organization. In this vein, one can begin to think of an ethnography of documentation. Therein, the key research questions revolve around the ways in which documents are used and integrated into specific kinds of organizational settings, as well as with how documents are exchanged and how they circulate within such settings. Clearly, documents carry content—words, images, plans, ideas, patterns, and so forth—but the manner in which such material is called on and manipulated, and the way in which it functions, cannot be determined (though it may be constrained) by an analysis of content. Thus, Harper’s ( 1998 ) study of the use of economic reports inside the International Monetary Fund provides various examples of how “reports” can function to both differentiate and cohere work groups. In the same way. Henderson ( 1995 ) illustrated how engineering sketches and drawings can serve as what she calls conscription devices on the workshop floor.

Documents constitute a form of what Latour ( 1986 ) would refer to as “immutable mobiles,” and with an eye on the mobility of documents, it is worth noting an emerging interest in histories of knowledge that seek to examine how the same documents have been received and absorbed quite differently by different cultural networks (see, e.g., Burke, 2000 ). A parallel concern has arisen with regard to the newly emergent “geographies of knowledge” (see, e.g., Livingstone, 2005 ). In the history of science, there has also been an expressed interest in the biography of scientific objects (Latour, 1987 , p. 262) or of “epistemic things” (Rheinberger, 2000 )—tracing the history of objects independent of the “inventors” and “discoverers” to which such objects are conventionally attached. It is an approach that could be easily extended to the study of documents and is partly reflected in the earlier discussion concerning the meaning of the concept of well-being. Note how in all these cases a key consideration is how words and documents as “things” circulate and translate from one culture to another; issues of content are secondary.

Studying how documents are used and how they circulate can constitute an important area of research in its own right. Yet even those who focus on document use can be overly anthropocentric and subsequently overemphasize the potency of human action in relation to written text. In that light, it is interesting to consider ways in which we might reverse that emphasis and instead to study the potency of text and the manner in which documents can influence organizational activities as well as reflect them. Thus, Dorothy Winsor ( 1999 ), for example, examined the ways in which work orders drafted by engineers not only shape and fashion the practices and activities of engineering technicians but also construct “two different worlds” on the workshop floor.

In light of this, I will suggest a typology (Table 19.3 ) of the ways in which documents have come to be and can be considered in social research.

While accepting that no form of categorical classification can capture the inherent fluidity of the world, its actors, and its objects, Table 19.3 aims to offer some understanding of the various ways in which documents have been dealt with by social researchers. Thus, approaches that fit into Cell 1 have been dominant in the history of social science generally. Therein, documents (especially as text) have been analyzed and coded for what they contain in the way of descriptions, reports, images, representations, and accounts. In short, they have been scoured for evidence. Data analysis strategies concentrate almost entirely on what is in the “text” (via various forms of CTA). This emphasis on content is carried over into Cell 2–type approaches, with the key differences being that analysis is concerned with how document content comes into being. The attention here is usually on the conceptual architecture and sociotechnical procedures by means of which written reports, descriptions, statistical data, and so forth are generated. Various kinds of discourse analysis have been used to unravel the conceptual issues, while a focus on sociotechnical and rule-based procedures by means of which clinical, police, social work, and other forms of records and reports are constructed has been well represented in the work of ethnomethodologists (see Prior, 2011 ). In contrast, and in Cell 3, the research focus is on the ways in which documents are called on as a resource by various and different kinds of “user.” Here, concerns with document content or how a document has come into being are marginal, and the analysis concentrates on the relationship between specific documents and their use or recruitment by identifiable human actors for purposeful ends. I have pointed to some studies of the latter kind in earlier paragraphs (e.g., Henderson, 1995 ). Finally, the approaches that fit into Cell 4 also position content as secondary. The emphasis here is on how documents as “things” function in schemes of social activity and with how such things can drive, rather than be driven by, human actors. In short, the spotlight is on the vita activa of documentation, and I have provided numerous example of documents as actors in other publications (see Prior, 2003 , 2008 , 2011 ).

Content analysis was a method originally developed to analyze mass media “messages” in an age of radio and newspaper print, well before the digital age. Unfortunately, CTA struggles to break free of its origins and continues to be associated with the quantitative analysis of “communication.” Yet, as I have argued, there is no rational reason why its use must be restricted to such a narrow field, because it can be used to analyze printed text and interview data (as well as other forms of inscription) in various settings. What it cannot overcome is the fact that it is a method of analysis and not a method of data collection. However, as I have shown, it is an analytical strategy that can be integrated into a variety of research designs and approaches—cross-sectional and longitudinal survey designs, ethnography and other forms of qualitative design, and secondary analysis of preexisting data sets. Even as a method of analysis, it is flexible and can be used either independent of other methods or in conjunction with them. As we have seen, it is easily merged with various forms of discourse analysis and can be used as an exploratory method or as a means of verification. Above all, perhaps, it crosses the divide between “quantitative” and “qualitative” modes of inquiry in social research and offers a new dimension to the meaning of mixed methods research. I recommend it.

Abbott, A. ( 1992 ). What do cases do? In C. C. Ragin & H. S. Becker (Eds.), What is a case? Exploring the foundations of social inquiry (pp. 53–82). Cambridge, England: Cambridge University Press.

Google Scholar

Google Preview

Altheide, D. L. ( 1987 ). Ethnographic content analysis.   Qualitative Sociology, 10, 65–77.

Arksey, H. , & O’Malley, L. ( 2005 ). Scoping studies: Towards a methodological framework.   International Journal of Sociological Research Methodology, 8, 19–32.

Babbie, E. ( 2013 ). The practice of social research (13th ed.) Belmont, CA: Wadsworth.

Bazerman, C. ( 1988 ). Shaping written knowledge. The genre and activity of the experimental article in science . Madison: University of Wisconsin Press.

Becker, G. ( 1997 ). Disrupted lives. How people create meaning in a chaotic world . London, England: University of California Press.

Berelson, B. ( 1952 ). Content analysis in communication research . Glencoe, IL: Free Press.

Bowker, G. C. , & Star, S. L. ( 1999 ). Sorting things out. Classification and its consequences . Cambridge, MA: MIT Press.

Braun, V. , & Clarke, V. ( 2006 ). Using thematic analysis in psychology.   Qualitative Research in Psychology, 3, 77–101.

Breuer, J. , & Freud, S. ( 2001 ). Studies on hysteria. In L. Strachey (Ed.), The standard edition of the complete psychological works of Sigmund Freud (Vol. 2). London, England: Vintage.

Bryman, A. ( 2008 ). Social research methods (3rd ed.). Oxford, England: Oxford University Press.

Burke, P. ( 2000 ). A social history of knowledge. From Guttenberg to Diderot . Cambridge, MA: Polity Press.

Bury, M. ( 1982 ). Chronic illness as biographical disruption.   Sociology of Health and Illness, 4, 167–182.

Carley, K. ( 1993 ). Coding choices for textual analysis. A comparison of content analysis and map analysis.   Sociological Methodology, 23, 75–126.

Charon, R. ( 2006 ). Narrative medicine. Honoring the stories of illness . New York, NY: Oxford University Press.

Creswell, J. W. ( 2007 ). Designing and conducting mixed methods research . Thousand Oaks, CA: Sage.

Davison, C. , Davey-Smith, G. , & Frankel, S. ( 1991 ). Lay epidemiology and the prevention paradox.   Sociology of Health & Illness, 13, 1–19.

Evans, M. , Prout, H. , Prior, L. , Tapper-Jones, L. , & Butler, C. ( 2007 ). A qualitative study of lay beliefs about influenza.   British Journal of General Practice, 57, 352–358.

Foucault, M. ( 1970 ). The order of things. An archaeology of the human sciences . London, England: Tavistock.

Frank, A. ( 1995 ). The wounded storyteller: Body, illness, and ethics . Chicago, IL: University of Chicago Press.

Gerring, J. ( 2004 ). What is a case study, and what is it good for?   The American Political Science Review, 98, 341–354.

Gilbert, G. N. , & Mulkay, M. ( 1984 ). Opening Pandora’s box. A sociological analysis of scientists’ discourse . Cambridge, England: Cambridge University Press.

Glaser, B. G. , & Strauss, A. L. ( 1967 ). The discovery of grounded theory. Strategies for qualitative research . New York, NY: Aldine de Gruyter.

Goode, W. J. , & Hatt, P. K. ( 1952 ). Methods in social research . New York, NY: McGraw–Hill.

Greimas, A. J. ( 1970 ). Du Sens. Essays sémiotiques . Paris, France: Ėditions du Seuil.

Habermas, J. ( 1987 ). The theory of communicative action: Vol.2, A critique of functionalist reason ( T. McCarthy , Trans.). Cambridge, MA: Polity Press.

Harper, R. ( 1998 ). Inside the IMF. An ethnography of documents, technology, and organizational action . London, England: Academic Press.

Henderson, K. ( 1995 ). The political career of a prototype. Visual representation in design engineering.   Social Problems, 42, 274–299.

Heritage, J. ( 1991 ). Garkfinkel and ethnomethodology . Cambridge, MA: Polity Press.

Hydén, L-C. ( 1997 ). Illness and narrative.   Sociology of Health & Illness, 19, 48–69.

Kahn, R. , & Cannell, C. ( 1957 ). The dynamics of interviewing. Theory, technique and cases . New York, NY: Wiley.

Kay, L. E. ( 2000 ). Who wrote the book of life? A history of the genetic code . Stanford, CA: Stanford University Press.

Kleinman, A. , Eisenberg, L. , & Good, B. ( 1978 ). Culture, illness & care, clinical lessons from anthropologic and cross-cultural research.   Annals of Internal Medicine, 88, 251–258.

Kracauer, S. ( 1952 ). The challenge of qualitative content analysis.   Public Opinion Quarterly, Special Issue on International Communications Research (1952–53), 16, 631–642.

Krippendorf, K. ( 2004 ). Content analysis: An introduction to its methodology (2nd ed.). Thousand Oaks, CA: Sage.

Latour, B. ( 1986 ). Visualization and cognition: Thinking with eyes and hands. Knowledge and Society, Studies in Sociology of Culture, Past and Present, 6, 1–40.

Latour, B. ( 1987 ). Science in action. How to follow scientists and engineers through society . Milton Keynes, England: Open University Press.

Livingstone, D. N. ( 2005 ). Text, talk, and testimony: Geographical reflections on scientific habits. An afterword.   British Society for the History of Science, 38, 93–100.

Luria, A. R. ( 1975 ). The man with the shattered world. A history of a brain wound ( L. Solotaroff , Trans.). Harmondsworth, England: Penguin.

Martin, A. , & Lynch, M. ( 2009 ). Counting things and counting people: The practices and politics of counting.   Social Problems, 56, 243–266.

Merton, R. K. ( 1968 ). Social theory and social structure . New York, NY: Free Press.

Morgan, D. L. ( 1993 ). Qualitative content analysis. A guide to paths not taken.   Qualitative Health Research, 2, 112–121.

Morgan, D. L. ( 1998 ). Practical strategies for combining qualitative and quantitative methods.   Qualitative Health Research, 8, 362–376.

Morris, P. G. , Prior, L. , Deb, S. , Lewis, G. , Mayle, W. , Burrow, C. E. , & Bryant, E. ( 2005 ). Patients’ views on outcome following head injury: A qualitative study,   BMC Family Practice, 6, 30.

Neuendorf, K. A. ( 2002 ). The content analysis guidebook . Thousand Oaks: CA: Sage.

Newman, J. , & Vidler, E. ( 2006 ). Discriminating customers, responsible patients, empowered users: Consumerism and the modernisation of health care,   Journal of Social Policy, 35, 193–210.

Office for National Statistics. ( 2012 ). First ONS annual experimental subjective well-being results . London, England: Office for National Statistics. Retrieved from http://www.ons.gov.uk/ons/dcp171766_272294.pdf

Prior, L. ( 2003 ). Using documents in social research . London, England: Sage.

Prior, L. ( 2008 ). Repositioning documents in social research.   Sociology. Special Issue on Research Methods, 42, 821–836.

Prior, L. ( 2011 ). Using documents and records in social research (4 vols.). London, England: Sage.

Prior, L. , Evans, M. , & Prout, H. ( 2011 ). Talking about colds and flu: The lay diagnosis of two common illnesses among older British people.   Social Science and Medicine, 73, 922–928.

Prior, L. , Hughes, D. , & Peckham, S. ( 2012 ) The discursive turn in policy analysis and the validation of policy stories.   Journal of Social Policy, 41, 271–289.

Ragin, C. C. , & Becker, H. S. ( 1992 ). What is a case? Exploring the foundations of social inquiry . Cambridge, England: Cambridge University Press.

Rheinberger, H.-J. ( 2000 ). Cytoplasmic particles. The trajectory of a scientific object. In Daston, L. (Ed.), Biographies of scientific objects (pp. 270–294). Chicago, IL: Chicago University Press.

Ricoeur, P. ( 1984 ). Time and narrative (Vol. 1., K. McLaughlin & D, Pellauer, Trans.). Chicago, IL: University of Chicago Press.

Roe, E. ( 1994 ). Narrative policy analysis, theory and practice . Durham, NC: Duke University Press.

Ryan, G. W. , & Bernard, H. R. ( 2000 ). Data management and analysis methods. In N. K. Denzin & Y. S. Lincoln (Eds.), Handbook of qualitative research (2nd ed., pp. 769–802). Thousand Oaks, CA: Sage.

Schutz, A. , & Luckman, T. ( 1974 ). The structures of the life-world (R. M. Zaner & H. T. Engelhardt, Trans.). London, England: Heinemann.

SPSS. ( 2007 ). Text mining for Clementine . 12.0 User’s Guide. Chicago, IL: SPSS.

Weber, R. P. ( 1990 ). Basic content analysis . Newbury Park, CA: Sage.

Winsor, D. ( 1999 ). Genre and activity systems. The role of documentation in maintaining and changing engineering activity systems.   Written Communication, 16, 200–224.

Zimmerman, D. H. , & Pollner, M. ( 1971 ). The everyday world as a phenomenon. In J. D. Douglas (Ed.), Understanding everyday life (pp. 80–103). London, England: Routledge & Kegan Paul.

• About Oxford Academic
• Publish journals with us
• University press partners
• What we publish
• New features  
• Open access
• Institutional account management
• Rights and permissions
• Get help with access
• Accessibility
• Advertising
• Media enquiries
• Oxford University Press
• Oxford Languages
• University of Oxford

Oxford University Press is a department of the University of Oxford. It furthers the University's objective of excellence in research, scholarship, and education by publishing worldwide

• Copyright © 2024 Oxford University Press
• Cookie settings
• Cookie policy
• Privacy policy
• Legal notice

This Feature Is Available To Subscribers Only

Sign In or Create an Account

This PDF is available to Subscribers Only

For full access to this pdf, sign in to an existing account, or purchase an annual subscription.

• Skip to main content
• Skip to primary sidebar
• Skip to footer
• QuestionPro

• Solutions Industries Gaming Automotive Sports and events Education Government Travel & Hospitality Financial Services Healthcare Cannabis Technology Use Case NPS+ Communities Audience Contactless surveys Mobile LivePolls Member Experience GDPR Positive People Science 360 Feedback Surveys
• Resources Blog eBooks Survey Templates Case Studies Training Help center

Home Market Research

Content Analysis: What is it in Qualitative Studies?

Have you ever wondered how qualitative researchers dig deep into the meanings packed into text, visual, and audio content? Consider a method that acts as guidance, guiding you across the tricky surroundings of analysis and interpretation. This is where content analysis comes in.

It is an approach that enables you to examine qualitative data such as words, images, and concepts more thoroughly. If you’ve ever been captivated by the complex details created within texts, photos, or spoken words, content analysis is your ticket to finding the hidden layers of meaning.

Get ready to discover how you can sort through the sea of qualitative information around you to identify patterns and draw significant conclusions. Keep reading to learn more about content analysis in qualitative studies and how to do it.

What is Content Analysis in Qualitative Studies

Content analysis is a method used in qualitative studies that empowers you to analyze and understand various types of content, such as an interview transcript, a collection of social media posts, or a series of photographs.

Simply said, content analysis is your toolkit for transforming raw data into useful insights. It involves more than just reading or observing. It’s about refining the key points, categorizing the differences, and identifying repeating patterns that could otherwise slip through the gaps.

Whether you’re a social scientist reading historical patterns or a psychologist diving into the complexities of human behavior, content analysis can help. Through this method, you can unlock layers of insight that enrich your understanding of the subject matter and contribute to the broader knowledge.

Content analysis aims to systematically analyze content to extract meaningful insights and patterns from the data. The primary goals of content analysis in qualitative research include:

• Understanding and interpreting the underlying meanings and nuances within the data.
• Identifying recurring patterns, themes, and concepts that emerge from the content.
• Contextualizing data within its broader social, cultural, or historical context.
• Validating or extending existing theories.
• Summarizing and synthesizing information.
• Identifying propaganda and communication bias.
• Highlighting communication gaps in different circumstances.

Importance of Content Analysis in Qualitative Research

Content analysis is one of the crucial qualitative research methods that systematically analyzes and interprets data to extract meaningful insights and understand patterns. It is crucial for a number of reasons in qualitative research. Some key reasons are listed below:

• To Gain Deep Insight: Content analysis enables you to identify hidden meanings, implicit messages, and underlying themes, allowing for a thorough understanding of your data.
• To Recognize Patterns: You can spot trends, attitudes, and behaviors contained in your content by identifying recurrent patterns and themes.
• To Understand Context: The analysis puts your data within a larger context to show how social, cultural, and historical trends shape your research information.
• To Develop Ideas: Qualitative Content analysis actively contributes to developing and improving your research ideas by identifying concepts, relationships, and connections within your data.
• To Make Informed Decisions: Content analysis insights lead your evidence-based decision-making across several domains, influencing strategies, policies, and communication approaches.

Types of Data Suitable for Content Analysis

When considering the types of data that are suitable for content analysis, it is important to identify the wide range of sources that can give meaningful insights. Content analysis is a versatile method that may be used for various data types, each with its unique perspective.

Here, we’ll look at three types of data that are particularly well-suited for content analysis:

Textual Data: Documents, Transcripts, Texts

Textual data is the foundation of content analysis. It contains a wide range of information that is embedded inside written or typed words. You can study documents such as research papers, publications, and government reports to reveal hidden themes and extract important patterns.

Transcripts of interviews, focus groups, or conversations are a valuable source of personal accounts that allow you to gain insight into the complexity of participants’ language and ideas. Literary writings, social media posts, and even historical documents can all be subjected to content analysis, and it can expose hidden layers of meaning.

Visual Data: Images, Photographs, Artifacts

Visual data, which includes images, photographs, and artifacts, brings a new level to content analysis. These visual contents can convey emotions, cultural settings, and societal trends that would be difficult to explain through textual data.

You may discover symbols, visual metaphors, and design choices that help to increase your understanding of the subject matter by thoroughly studying visual content.

Whether you’re researching artworks, historical images, or modern visual communication, qualitative analysis of visual data can assist you in understanding the visual language hidden in these sources.

Audiovisual Data: Videos, Audio Recordings, Multimedia

Videos and multimedia contents provide an immersive experience. It enables you to observe nonverbal cues, gestures, and interactions. Audio recordings capture vocal details, intonations, and emotions that textual analysis may overlook.

You can gain an understanding of complex interpersonal dynamics, cultural expressions, and the interaction of verbal and nonverbal communication by evaluating audiovisual content.

Key Steps in Conducting Content Analysis

A systematic framework will help you when you start your content analysis project and will lead you through the process of drawing out valuable insights from your data. Most qualitative analysis methods use this approach to study and analyze.

By following these procedures, you may be confident that your analysis is comprehensive, organized, and able to uncover the content’s hidden layers. Let’s explore these steps:

Step 1: Data Collection and Preparation

Data gathering and preparation are the first steps on the qualitative content analysis journey. Gather your dataset’s documents, transcripts, photographs, or audiovisual contents.

Make sure the data is relevant to the goals of your study and covers the range of facts you want to investigate. Organize and structure your data so that it can be quickly accessible for analysis. This step sets the groundwork for the next in-depth analysis.

Step 2: Familiarization with Data

Observe the textual data, examine images, or listen to recordings several times. This involvement will help you get familiar with the information, recognize variations, and understand the context. As you read through the information, take down your initial ideas, questions, and create themes.

Step 3: Initial Coding

Begin by dividing the data into smaller, more relevant pieces. As you engage with each piece of content, assign labels that summarize the data.

Allow new rules to develop naturally by remaining open-minded and experimental. This step requires careful attention to detail and enables you to discover underlying patterns and themes that may not be visible at first.

Step 4: Developing Categories

With a set of basic rules in hand, it’s time to create categories using the axial coding process. Begin categorizing relevant codes together to construct larger topics or groups. This coding process entails structuring the files according to their conceptual links, similar to a relational analysis.

By categorizing your data, you build a framework that highlights the overall concepts and relationships found in the information. This statistical analysis stage clarifies and structures your qualitative data analysis.

Step 5: Refining and Selecting Codes

During this stage, you will refine and pick the most important categories and tags that best reflect the purpose of your data. Analyze and examine the relationships between categories, identifying the key themes that arise.

This refinement research technique allows you to reduce the complexity of your data to a clear and coherent narrative. The codes and categories you choose will serve as the foundation for your final analysis and interpretation.

Step 6: Analyzing Themes and Patterns

Observe the emerging themes and patterns using your improved codes and categories. These themes capture the key ideas and insights included in your data. Consider the frequency, significance, and relationships between various codes and categories.

• Identifying New Themes: Pay close attention to the topics that arise naturally from your data. These themes represent your analysis’s key messages, points of view, or phenomena.
• Recognizing Patterns and Relationships: Identify complex patterns and linkages between categories and topics. These connections provide more information on the interrelationships of ideas in your qualitative data.

Step 7: Interpreting and Reporting Findings

As you are going to interpret and report your findings, follow these crucial actions:

• Extracting Meaning from Coded Data: Examine your coded data for relevance. Investigate how individual codes and categories contribute to the overall picture. Consider how each theme affects your research goals.
• Contextualizing Themes: Contextualize your concepts within the structure of your research. Discuss their connections to existing literature, societal trends, or historical influences. This context adds to the complex nature and relevance of your findings.
• Communicating Findings Effectively: Create a clear and solid script that explains your results effectively. To explain crucial ideas, use descriptive language, data snippets, and graphic elements. Your goal is to communicate your ideas in a compelling and understandable manner.

Step 8: Enhancing Validity and Reliability

It is critical to ensure the validity and reliability of your qualitative research in order to produce credible and trustworthy results. Here are some strategies you can use in your content analysis:

• Triangulation: Strengthen your findings by collecting data from different sources, employing various research methods, and collaborating with multiple researchers.
• Member Checking and Peer Review: Validate your results by obtaining feedback from participants (member checking) and fellow researchers (peer review).
• Addressing Researcher Bias: To reduce bias, be conscious of your own assumptions, make transparent decisions, and consider your influence throughout the study process.

Applications of Content Analysis in Qualitative Research

You can find content analysis to be a versatile and powerful research method within qualitative research, which enables you to extract meaningful insights and patterns from various types of data. Here are some essential uses of content analysis to consider:

Social Sciences

In your social science research, you can apply content analysis to various areas, such as investigating social media, online communities, and digital communication, as well as analyzing interviews, focus groups, and other qualitative data.

Media Studies

In media research, you can use content analysis to study how different groups, like race, gender, and sexual orientation, are portrayed in media. You can also analyze media framing, bias, and its impact.

Health Sciences

You can utilize content analysis to examine health communication in qualitative health research. This involves analyzing how the media presents health topics, assessing the effectiveness of health campaigns, and comprehending how health messages impact individuals’ behavioral responses.

Political Communication

In your political communication research, content analysis enables you to examine elements like political speeches, debates, and news reporting on political occurrences. You can also analyze political ads and investigate how political communication shapes public opinion and voting tendencies.

Marketing Research

In marketing research, you can utilize content analysis to examine ads, customer reviews, and social media posts about products or services. It can offer you insights into your customers’ preferences, attitudes, and actions.

Education Research

You can employ content analysis to examine educational materials like textbooks, curricula, and instructional resources in your education research. It can offer you valuable insights into how various subjects, viewpoints, and values are portrayed.

Ethical Considerations in Content Analysis

Make sure to undertake content analysis while carefully navigating the ethical context. To bear in mind specifically are the following:

• Privacy and Confidentiality: Respect the privacy of the people whose data you are analyzing. Secure sensitive information and avoid disclosing identities to ensure the confidentiality of your studies.
• Attribution and Plagiarism: Follow proper attribution requirements when crediting sources or recreating information. To avoid plagiarism, give credit to the original creators and sources.
• Informed Consent: When using data from human participants, prioritize informed permission. Assure that they understand how their data will be handled and provide free, informed consent.

Content Analysis vs. Grounded Theory

It is important to distinguish between content analysis and grounded theory when choosing qualitative methods:

• Content analysis: The process of carefully reviewing data to uncover patterns, themes, and meanings is known as content analysis. It focuses more on data-driven exploration.
• Grounded Theory: On the other hand, it is a process of developing theories based on data. It seeks to construct theories by systematic data analysis, allowing themes and concepts to emerge and create the theory itself.

Understanding these distinctions can help you select the best technique for your research targets.

As you wrap up your exploration, it’s clear that content analysis plays a crucial role in qualitative studies. Its unique capacity to extract significant insights and patterns from various data sources defines it as a versatile research tool.

In research, quantitative and qualitative approaches complement one another. Remember that content analysis is your gateway to unraveling the richness and intricacies of data, which will give dimension to your qualitative research efforts.

QuestionPro can be an essential study tool in the field of qualitative content analysis. Its extensive features allow for rapid data collection and management, making it a vital study tool. Using its configurable survey and questionnaire choices, you may simply collect user textual, visual, or audio data.

The data management tools of the platform simplify the coding and categorization process, allowing you to evaluate and comprehend your data methodically. Furthermore, QuestionPro provides extensive analytical tools to help you identify developing themes and trends, enabling a thorough content analysis.

By utilizing QuestionPro’s capabilities, researchers can improve the validity and reliability of their qualitative research while revealing significant insights from different data sources.

LEARN MORE         FREE TRIAL

MORE LIKE THIS

21 Best Customer Advocacy Software for Customers in 2024

Apr 19, 2024

10 Quantitative Data Analysis Software for Every Data Scientist

Apr 18, 2024

11 Best Enterprise Feedback Management Software in 2024

17 Best Online Reputation Management Software in 2024

Apr 17, 2024

Other categories

• Academic Research
• Artificial Intelligence
• Assessments
• Brand Awareness
• Case Studies
• Communities
• Consumer Insights
• Customer effort score
• Customer Engagement
• Customer Experience
• Customer Loyalty
• Customer Research
• Customer Satisfaction
• Employee Benefits
• Employee Engagement
• Employee Retention
• Friday Five
• General Data Protection Regulation
• Insights Hub
• Life@QuestionPro
• Market Research
• Mobile diaries
• Mobile Surveys
• New Features
• Online Communities
• Question Types
• Questionnaire
• QuestionPro Products
• Release Notes
• Research Tools and Apps
• Revenue at Risk
• Survey Templates
• Training Tips
• Uncategorized
• Video Learning Series
• What’s Coming Up
• Workforce Intelligence

• Privacy Policy

Buy Me a Coffee

Home » Case Study – Methods, Examples and Guide

Case Study – Methods, Examples and Guide

Table of Contents

A case study is a research method that involves an in-depth examination and analysis of a particular phenomenon or case, such as an individual, organization, community, event, or situation.

It is a qualitative research approach that aims to provide a detailed and comprehensive understanding of the case being studied. Case studies typically involve multiple sources of data, including interviews, observations, documents, and artifacts, which are analyzed using various techniques, such as content analysis, thematic analysis, and grounded theory. The findings of a case study are often used to develop theories, inform policy or practice, or generate new research questions.

Types of Case Study

Types and Methods of Case Study are as follows:

Single-Case Study

A single-case study is an in-depth analysis of a single case. This type of case study is useful when the researcher wants to understand a specific phenomenon in detail.

For Example , A researcher might conduct a single-case study on a particular individual to understand their experiences with a particular health condition or a specific organization to explore their management practices. The researcher collects data from multiple sources, such as interviews, observations, and documents, and uses various techniques to analyze the data, such as content analysis or thematic analysis. The findings of a single-case study are often used to generate new research questions, develop theories, or inform policy or practice.

Multiple-Case Study

A multiple-case study involves the analysis of several cases that are similar in nature. This type of case study is useful when the researcher wants to identify similarities and differences between the cases.

For Example, a researcher might conduct a multiple-case study on several companies to explore the factors that contribute to their success or failure. The researcher collects data from each case, compares and contrasts the findings, and uses various techniques to analyze the data, such as comparative analysis or pattern-matching. The findings of a multiple-case study can be used to develop theories, inform policy or practice, or generate new research questions.

Exploratory Case Study

An exploratory case study is used to explore a new or understudied phenomenon. This type of case study is useful when the researcher wants to generate hypotheses or theories about the phenomenon.

For Example, a researcher might conduct an exploratory case study on a new technology to understand its potential impact on society. The researcher collects data from multiple sources, such as interviews, observations, and documents, and uses various techniques to analyze the data, such as grounded theory or content analysis. The findings of an exploratory case study can be used to generate new research questions, develop theories, or inform policy or practice.

Descriptive Case Study

A descriptive case study is used to describe a particular phenomenon in detail. This type of case study is useful when the researcher wants to provide a comprehensive account of the phenomenon.

For Example, a researcher might conduct a descriptive case study on a particular community to understand its social and economic characteristics. The researcher collects data from multiple sources, such as interviews, observations, and documents, and uses various techniques to analyze the data, such as content analysis or thematic analysis. The findings of a descriptive case study can be used to inform policy or practice or generate new research questions.

Instrumental Case Study

An instrumental case study is used to understand a particular phenomenon that is instrumental in achieving a particular goal. This type of case study is useful when the researcher wants to understand the role of the phenomenon in achieving the goal.

For Example, a researcher might conduct an instrumental case study on a particular policy to understand its impact on achieving a particular goal, such as reducing poverty. The researcher collects data from multiple sources, such as interviews, observations, and documents, and uses various techniques to analyze the data, such as content analysis or thematic analysis. The findings of an instrumental case study can be used to inform policy or practice or generate new research questions.

Case Study Data Collection Methods

Here are some common data collection methods for case studies:

Interviews involve asking questions to individuals who have knowledge or experience relevant to the case study. Interviews can be structured (where the same questions are asked to all participants) or unstructured (where the interviewer follows up on the responses with further questions). Interviews can be conducted in person, over the phone, or through video conferencing.

Observations

Observations involve watching and recording the behavior and activities of individuals or groups relevant to the case study. Observations can be participant (where the researcher actively participates in the activities) or non-participant (where the researcher observes from a distance). Observations can be recorded using notes, audio or video recordings, or photographs.

Documents can be used as a source of information for case studies. Documents can include reports, memos, emails, letters, and other written materials related to the case study. Documents can be collected from the case study participants or from public sources.

Surveys involve asking a set of questions to a sample of individuals relevant to the case study. Surveys can be administered in person, over the phone, through mail or email, or online. Surveys can be used to gather information on attitudes, opinions, or behaviors related to the case study.

Artifacts are physical objects relevant to the case study. Artifacts can include tools, equipment, products, or other objects that provide insights into the case study phenomenon.

How to conduct Case Study Research

Conducting a case study research involves several steps that need to be followed to ensure the quality and rigor of the study. Here are the steps to conduct case study research:

• Define the research questions: The first step in conducting a case study research is to define the research questions. The research questions should be specific, measurable, and relevant to the case study phenomenon under investigation.
• Select the case: The next step is to select the case or cases to be studied. The case should be relevant to the research questions and should provide rich and diverse data that can be used to answer the research questions.
• Collect data: Data can be collected using various methods, such as interviews, observations, documents, surveys, and artifacts. The data collection method should be selected based on the research questions and the nature of the case study phenomenon.
• Analyze the data: The data collected from the case study should be analyzed using various techniques, such as content analysis, thematic analysis, or grounded theory. The analysis should be guided by the research questions and should aim to provide insights and conclusions relevant to the research questions.
• Draw conclusions: The conclusions drawn from the case study should be based on the data analysis and should be relevant to the research questions. The conclusions should be supported by evidence and should be clearly stated.
• Validate the findings: The findings of the case study should be validated by reviewing the data and the analysis with participants or other experts in the field. This helps to ensure the validity and reliability of the findings.
• Write the report: The final step is to write the report of the case study research. The report should provide a clear description of the case study phenomenon, the research questions, the data collection methods, the data analysis, the findings, and the conclusions. The report should be written in a clear and concise manner and should follow the guidelines for academic writing.

Examples of Case Study

Here are some examples of case study research:

• The Hawthorne Studies : Conducted between 1924 and 1932, the Hawthorne Studies were a series of case studies conducted by Elton Mayo and his colleagues to examine the impact of work environment on employee productivity. The studies were conducted at the Hawthorne Works plant of the Western Electric Company in Chicago and included interviews, observations, and experiments.
• The Stanford Prison Experiment: Conducted in 1971, the Stanford Prison Experiment was a case study conducted by Philip Zimbardo to examine the psychological effects of power and authority. The study involved simulating a prison environment and assigning participants to the role of guards or prisoners. The study was controversial due to the ethical issues it raised.
• The Challenger Disaster: The Challenger Disaster was a case study conducted to examine the causes of the Space Shuttle Challenger explosion in 1986. The study included interviews, observations, and analysis of data to identify the technical, organizational, and cultural factors that contributed to the disaster.
• The Enron Scandal: The Enron Scandal was a case study conducted to examine the causes of the Enron Corporation’s bankruptcy in 2001. The study included interviews, analysis of financial data, and review of documents to identify the accounting practices, corporate culture, and ethical issues that led to the company’s downfall.
• The Fukushima Nuclear Disaster : The Fukushima Nuclear Disaster was a case study conducted to examine the causes of the nuclear accident that occurred at the Fukushima Daiichi Nuclear Power Plant in Japan in 2011. The study included interviews, analysis of data, and review of documents to identify the technical, organizational, and cultural factors that contributed to the disaster.

Application of Case Study

Case studies have a wide range of applications across various fields and industries. Here are some examples:

Business and Management

Case studies are widely used in business and management to examine real-life situations and develop problem-solving skills. Case studies can help students and professionals to develop a deep understanding of business concepts, theories, and best practices.

Case studies are used in healthcare to examine patient care, treatment options, and outcomes. Case studies can help healthcare professionals to develop critical thinking skills, diagnose complex medical conditions, and develop effective treatment plans.

Case studies are used in education to examine teaching and learning practices. Case studies can help educators to develop effective teaching strategies, evaluate student progress, and identify areas for improvement.

Social Sciences

Case studies are widely used in social sciences to examine human behavior, social phenomena, and cultural practices. Case studies can help researchers to develop theories, test hypotheses, and gain insights into complex social issues.

Law and Ethics

Case studies are used in law and ethics to examine legal and ethical dilemmas. Case studies can help lawyers, policymakers, and ethical professionals to develop critical thinking skills, analyze complex cases, and make informed decisions.

Purpose of Case Study

The purpose of a case study is to provide a detailed analysis of a specific phenomenon, issue, or problem in its real-life context. A case study is a qualitative research method that involves the in-depth exploration and analysis of a particular case, which can be an individual, group, organization, event, or community.

The primary purpose of a case study is to generate a comprehensive and nuanced understanding of the case, including its history, context, and dynamics. Case studies can help researchers to identify and examine the underlying factors, processes, and mechanisms that contribute to the case and its outcomes. This can help to develop a more accurate and detailed understanding of the case, which can inform future research, practice, or policy.

Case studies can also serve other purposes, including:

• Illustrating a theory or concept: Case studies can be used to illustrate and explain theoretical concepts and frameworks, providing concrete examples of how they can be applied in real-life situations.
• Developing hypotheses: Case studies can help to generate hypotheses about the causal relationships between different factors and outcomes, which can be tested through further research.
• Providing insight into complex issues: Case studies can provide insights into complex and multifaceted issues, which may be difficult to understand through other research methods.
• Informing practice or policy: Case studies can be used to inform practice or policy by identifying best practices, lessons learned, or areas for improvement.

Advantages of Case Study Research

There are several advantages of case study research, including:

• In-depth exploration: Case study research allows for a detailed exploration and analysis of a specific phenomenon, issue, or problem in its real-life context. This can provide a comprehensive understanding of the case and its dynamics, which may not be possible through other research methods.
• Rich data: Case study research can generate rich and detailed data, including qualitative data such as interviews, observations, and documents. This can provide a nuanced understanding of the case and its complexity.
• Holistic perspective: Case study research allows for a holistic perspective of the case, taking into account the various factors, processes, and mechanisms that contribute to the case and its outcomes. This can help to develop a more accurate and comprehensive understanding of the case.
• Theory development: Case study research can help to develop and refine theories and concepts by providing empirical evidence and concrete examples of how they can be applied in real-life situations.
• Practical application: Case study research can inform practice or policy by identifying best practices, lessons learned, or areas for improvement.
• Contextualization: Case study research takes into account the specific context in which the case is situated, which can help to understand how the case is influenced by the social, cultural, and historical factors of its environment.

Limitations of Case Study Research

There are several limitations of case study research, including:

• Limited generalizability : Case studies are typically focused on a single case or a small number of cases, which limits the generalizability of the findings. The unique characteristics of the case may not be applicable to other contexts or populations, which may limit the external validity of the research.
• Biased sampling: Case studies may rely on purposive or convenience sampling, which can introduce bias into the sample selection process. This may limit the representativeness of the sample and the generalizability of the findings.
• Subjectivity: Case studies rely on the interpretation of the researcher, which can introduce subjectivity into the analysis. The researcher’s own biases, assumptions, and perspectives may influence the findings, which may limit the objectivity of the research.
• Limited control: Case studies are typically conducted in naturalistic settings, which limits the control that the researcher has over the environment and the variables being studied. This may limit the ability to establish causal relationships between variables.
• Time-consuming: Case studies can be time-consuming to conduct, as they typically involve a detailed exploration and analysis of a specific case. This may limit the feasibility of conducting multiple case studies or conducting case studies in a timely manner.
• Resource-intensive: Case studies may require significant resources, including time, funding, and expertise. This may limit the ability of researchers to conduct case studies in resource-constrained settings.

About the author

Muhammad Hassan

Researcher, Academic Writer, Web developer

You may also like

Questionnaire – Definition, Types, and Examples

Observational Research – Methods and Guide

Quantitative Research – Methods, Types and...

Qualitative Research Methods

Explanatory Research – Types, Methods, Guide

Survey Research – Types, Methods, Examples

Research Design Review

A discussion of qualitative & quantitative research design, analyzability & a qualitative content analysis case study.

The following is a modified excerpt from Applied Qualitative Research Design: A Total Quality Framework Approach (Roller & Lavrakas, 2015, pp. 284-285).

Purpose & Scope The primary purpose of this primary qualitative content analysis study was to extend the existing literature on the portrayal of women’s roles in print media by examining the imagery and themes depicted of heterosexual college-educated women who leave the workforce to devote themselves to being stay-at-home mothers (a phenomenon referred to as “opting out”) across a wide, diverse range of print publications. More specifically, this research set out to investigate two areas of media coverage: the content (e.g., the women who are portrayed in the media and how they are described) and the context (e.g., the types of media and articles).

This study examined a 16-year period from 1988 to 2003. This 16-year period was chosen because 1988 was the earliest date on which the researchers had access to a searchable database for sampling, and 2003 was the year that the term “opting out” (referring to women leaving the workforce to become full-time mothers) became popular. The researchers identified 51 articles from 30 publications that represented a wide diversity of large-circulation print media. The researchers acknowledged that the sample “underrepresents articles appearing in small-town outlets” (p. 502).

Analyzability There are two aspects of the TQF Analyzability component — processing and verification. In terms of processing, the content data obtained by Kuperberg and Stone from coding revealed three primary patterns or themes in the depiction of women who opt out: “family first, child-centric”; “the mommy elite”; and “making choices.” The researchers discuss these themes at some length and support their findings by way of research literature and other references. In some instances, they report that their findings were in contrast to the literature (which presented an opportunity for future research in this area). Their final interpretation of the data includes their overall assertion that print media depict “traditional images of heterosexual women” (p. 510).

Important to the integrity of the analysis process, the researchers absorbed themselves in the sampled articles and, in doing so, identified inconsistencies in the research outcomes. For example, a careful reading of the articles revealed that many of the women depicted as stay-at-home mothers were actually employed in some form of paid work from home. The researchers also enriched the discussion of their findings by giving the reader some context relevant to the publications and articles. For example, they revealed that 45 of the 51 articles were from general interest newspapers or magazines, a fact that supports their research objective of analyzing print media that reach large, diverse audiences.

In terms of verification, the researchers performed a version of deviant case analysis in which they investigated contrary evidence to the assertion made by many articles that there is a growing trend in the proportion of women opting out. Citing research studies from the literature as well as actual trend data, the researchers stated that the articles’ claim that women were increasingly opting out had weak support.

Kuperberg, A., & Stone, P. (2008). The media depiction of women who opt out. Gender & Society , 22 (4), 497–517.

Share this:

• Click to share on Reddit (Opens in new window)
• Click to share on Twitter (Opens in new window)
• Click to share on LinkedIn (Opens in new window)
• Click to share on Facebook (Opens in new window)
• Click to share on Tumblr (Opens in new window)
• Click to email a link to a friend (Opens in new window)
• Click to print (Opens in new window)

Leave a comment Cancel reply

This site uses Akismet to reduce spam. Learn how your comment data is processed .

• Already have a WordPress.com account? Log in now.
• Subscribe Subscribed
• Copy shortlink
• Report this content
• View post in Reader
• Manage subscriptions
• Collapse this bar

Final dates! Join the tutor2u subject teams in London for a day of exam technique and revision at the cinema. Learn more →

Reference Library

Collections

• See what's new
• All Resources
• Student Resources
• Assessment Resources
• Teaching Resources
• CPD Courses
• Livestreams

Study notes, videos, interactive activities and more!

Psychology news, insights and enrichment

Currated collections of free resources

Browse resources by topic

• All Psychology Resources

Resource Selections

Currated lists of resources

• Study Notes

Content Analysis

Last updated 22 Mar 2021

• Share on Facebook
• Share on Twitter
• Share by Email

Content analysis is a method used to analyse qualitative data (non-numerical data). In its most common form it is a technique that allows a researcher to take qualitative data and to transform it into quantitative data (numerical data). The technique can be used for data in many different formats, for example interview transcripts, film, and audio recordings.

The researcher conducting a content analysis will use ‘coding units’ in their work. These units vary widely depending on the data used, but an example would be the number of positive or negative words used by a mother to describe her child’s behaviour or the number of swear words in a film.

The procedure for a content analysis is shown below:

Strengths of content analysis

It is a reliable way to analyse qualitative data as the coding units are not open to interpretation and so are applied in the same way over time and with different researchers

It is an easy technique to use and is not too time consuming

It allows a statistical analysis to be conducted if required as there is usually quantitative data as a result of the procedure

Weaknesses of content analysis

Causality cannot be established as it merely describes the data

As it only describes the data it cannot extract any deeper meaning or explanation for the data patterns arising.

• Content Analysis

You might also like

A level psychology topic quiz - research methods.

Quizzes & Activities

Research Methods: MCQ Revision Test 1 for AQA A Level Psychology

Topic Videos

Example Answers for Research Methods: A Level Psychology, Paper 2, June 2018 (AQA)

Exam Support

Our subjects

• › Criminology
• › Economics
• › Geography
• › Health & Social Care
• › Psychology
• › Sociology
• › Teaching & learning resources
• › Student revision workshops
• › Online student courses
• › CPD for teachers
• › Livestreams
• › Teaching jobs

Boston House, 214 High Street, Boston Spa, West Yorkshire, LS23 6AD Tel: 01937 848885

• › Contact us
• › Terms of use
• › Privacy & cookies

© 2002-2024 Tutor2u Limited. Company Reg no: 04489574. VAT reg no 816865400.

Organizing Your Social Sciences Research Assignments

• Annotated Bibliography
• Analyzing a Scholarly Journal Article
• Group Presentations
• Dealing with Nervousness
• Using Visual Aids
• Grading Someone Else's Paper
• Types of Structured Group Activities
• Group Project Survival Skills
• Leading a Class Discussion
• Multiple Book Review Essay
• Reviewing Collected Works
• Writing a Case Analysis Paper
• Writing a Case Study
• About Informed Consent
• Writing Field Notes
• Writing a Policy Memo
• Writing a Reflective Paper
• Writing a Research Proposal
• Generative AI and Writing
• Acknowledgments

Definition and Introduction

Case analysis is a problem-based teaching and learning method that involves critically analyzing complex scenarios within an organizational setting for the purpose of placing the student in a “real world” situation and applying reflection and critical thinking skills to contemplate appropriate solutions, decisions, or recommended courses of action. It is considered a more effective teaching technique than in-class role playing or simulation activities. The analytical process is often guided by questions provided by the instructor that ask students to contemplate relationships between the facts and critical incidents described in the case.

Cases generally include both descriptive and statistical elements and rely on students applying abductive reasoning to develop and argue for preferred or best outcomes [i.e., case scenarios rarely have a single correct or perfect answer based on the evidence provided]. Rather than emphasizing theories or concepts, case analysis assignments emphasize building a bridge of relevancy between abstract thinking and practical application and, by so doing, teaches the value of both within a specific area of professional practice.

Given this, the purpose of a case analysis paper is to present a structured and logically organized format for analyzing the case situation. It can be assigned to students individually or as a small group assignment and it may include an in-class presentation component. Case analysis is predominately taught in economics and business-related courses, but it is also a method of teaching and learning found in other applied social sciences disciplines, such as, social work, public relations, education, journalism, and public administration.

Ellet, William. The Case Study Handbook: A Student's Guide . Revised Edition. Boston, MA: Harvard Business School Publishing, 2018; Christoph Rasche and Achim Seisreiner. Guidelines for Business Case Analysis . University of Potsdam; Writing a Case Analysis . Writing Center, Baruch College; Volpe, Guglielmo. "Case Teaching in Economics: History, Practice and Evidence." Cogent Economics and Finance 3 (December 2015). doi:https://doi.org/10.1080/23322039.2015.1120977.

How to Approach Writing a Case Analysis Paper

The organization and structure of a case analysis paper can vary depending on the organizational setting, the situation, and how your professor wants you to approach the assignment. Nevertheless, preparing to write a case analysis paper involves several important steps. As Hawes notes, a case analysis assignment “...is useful in developing the ability to get to the heart of a problem, analyze it thoroughly, and to indicate the appropriate solution as well as how it should be implemented” [p.48]. This statement encapsulates how you should approach preparing to write a case analysis paper.

Before you begin to write your paper, consider the following analytical procedures:

• Review the case to get an overview of the situation . A case can be only a few pages in length, however, it is most often very lengthy and contains a significant amount of detailed background information and statistics, with multilayered descriptions of the scenario, the roles and behaviors of various stakeholder groups, and situational events. Therefore, a quick reading of the case will help you gain an overall sense of the situation and illuminate the types of issues and problems that you will need to address in your paper. If your professor has provided questions intended to help frame your analysis, use them to guide your initial reading of the case.
• Read the case thoroughly . After gaining a general overview of the case, carefully read the content again with the purpose of understanding key circumstances, events, and behaviors among stakeholder groups. Look for information or data that appears contradictory, extraneous, or misleading. At this point, you should be taking notes as you read because this will help you develop a general outline of your paper. The aim is to obtain a complete understanding of the situation so that you can begin contemplating tentative answers to any questions your professor has provided or, if they have not provided, developing answers to your own questions about the case scenario and its connection to the course readings,lectures, and class discussions.
• Determine key stakeholder groups, issues, and events and the relationships they all have to each other . As you analyze the content, pay particular attention to identifying individuals, groups, or organizations described in the case and identify evidence of any problems or issues of concern that impact the situation in a negative way. Other things to look for include identifying any assumptions being made by or about each stakeholder, potential biased explanations or actions, explicit demands or ultimatums , and the underlying concerns that motivate these behaviors among stakeholders. The goal at this stage is to develop a comprehensive understanding of the situational and behavioral dynamics of the case and the explicit and implicit consequences of each of these actions.
• Identify the core problems . The next step in most case analysis assignments is to discern what the core [i.e., most damaging, detrimental, injurious] problems are within the organizational setting and to determine their implications. The purpose at this stage of preparing to write your analysis paper is to distinguish between the symptoms of core problems and the core problems themselves and to decide which of these must be addressed immediately and which problems do not appear critical but may escalate over time. Identify evidence from the case to support your decisions by determining what information or data is essential to addressing the core problems and what information is not relevant or is misleading.
• Explore alternative solutions . As noted, case analysis scenarios rarely have only one correct answer. Therefore, it is important to keep in mind that the process of analyzing the case and diagnosing core problems, while based on evidence, is a subjective process open to various avenues of interpretation. This means that you must consider alternative solutions or courses of action by critically examining strengths and weaknesses, risk factors, and the differences between short and long-term solutions. For each possible solution or course of action, consider the consequences they may have related to their implementation and how these recommendations might lead to new problems. Also, consider thinking about your recommended solutions or courses of action in relation to issues of fairness, equity, and inclusion.
• Decide on a final set of recommendations . The last stage in preparing to write a case analysis paper is to assert an opinion or viewpoint about the recommendations needed to help resolve the core problems as you see them and to make a persuasive argument for supporting this point of view. Prepare a clear rationale for your recommendations based on examining each element of your analysis. Anticipate possible obstacles that could derail their implementation. Consider any counter-arguments that could be made concerning the validity of your recommended actions. Finally, describe a set of criteria and measurable indicators that could be applied to evaluating the effectiveness of your implementation plan.

Use these steps as the framework for writing your paper. Remember that the more detailed you are in taking notes as you critically examine each element of the case, the more information you will have to draw from when you begin to write. This will save you time.

NOTE : If the process of preparing to write a case analysis paper is assigned as a student group project, consider having each member of the group analyze a specific element of the case, including drafting answers to the corresponding questions used by your professor to frame the analysis. This will help make the analytical process more efficient and ensure that the distribution of work is equitable. This can also facilitate who is responsible for drafting each part of the final case analysis paper and, if applicable, the in-class presentation.

Framework for Case Analysis . College of Management. University of Massachusetts; Hawes, Jon M. "Teaching is Not Telling: The Case Method as a Form of Interactive Learning." Journal for Advancement of Marketing Education 5 (Winter 2004): 47-54; Rasche, Christoph and Achim Seisreiner. Guidelines for Business Case Analysis . University of Potsdam; Writing a Case Study Analysis . University of Arizona Global Campus Writing Center; Van Ness, Raymond K. A Guide to Case Analysis . School of Business. State University of New York, Albany; Writing a Case Analysis . Business School, University of New South Wales.

Structure and Writing Style

A case analysis paper should be detailed, concise, persuasive, clearly written, and professional in tone and in the use of language . As with other forms of college-level academic writing, declarative statements that convey information, provide a fact, or offer an explanation or any recommended courses of action should be based on evidence. If allowed by your professor, any external sources used to support your analysis, such as course readings, should be properly cited under a list of references. The organization and structure of case analysis papers can vary depending on your professor’s preferred format, but its structure generally follows the steps used for analyzing the case.

Introduction

The introduction should provide a succinct but thorough descriptive overview of the main facts, issues, and core problems of the case . The introduction should also include a brief summary of the most relevant details about the situation and organizational setting. This includes defining the theoretical framework or conceptual model on which any questions were used to frame your analysis.

Following the rules of most college-level research papers, the introduction should then inform the reader how the paper will be organized. This includes describing the major sections of the paper and the order in which they will be presented. Unless you are told to do so by your professor, you do not need to preview your final recommendations in the introduction. U nlike most college-level research papers , the introduction does not include a statement about the significance of your findings because a case analysis assignment does not involve contributing new knowledge about a research problem.

Background Analysis

Background analysis can vary depending on any guiding questions provided by your professor and the underlying concept or theory that the case is based upon. In general, however, this section of your paper should focus on:

• Providing an overarching analysis of problems identified from the case scenario, including identifying events that stakeholders find challenging or troublesome,
• Identifying assumptions made by each stakeholder and any apparent biases they may exhibit,
• Describing any demands or claims made by or forced upon key stakeholders, and
• Highlighting any issues of concern or complaints expressed by stakeholders in response to those demands or claims.

These aspects of the case are often in the form of behavioral responses expressed by individuals or groups within the organizational setting. However, note that problems in a case situation can also be reflected in data [or the lack thereof] and in the decision-making, operational, cultural, or institutional structure of the organization. Additionally, demands or claims can be either internal and external to the organization [e.g., a case analysis involving a president considering arms sales to Saudi Arabia could include managing internal demands from White House advisors as well as demands from members of Congress].

Throughout this section, present all relevant evidence from the case that supports your analysis. Do not simply claim there is a problem, an assumption, a demand, or a concern; tell the reader what part of the case informed how you identified these background elements.

Identification of Problems

In most case analysis assignments, there are problems, and then there are problems . Each problem can reflect a multitude of underlying symptoms that are detrimental to the interests of the organization. The purpose of identifying problems is to teach students how to differentiate between problems that vary in severity, impact, and relative importance. Given this, problems can be described in three general forms: those that must be addressed immediately, those that should be addressed but the impact is not severe, and those that do not require immediate attention and can be set aside for the time being.

All of the problems you identify from the case should be identified in this section of your paper, with a description based on evidence explaining the problem variances. If the assignment asks you to conduct research to further support your assessment of the problems, include this in your explanation. Remember to cite those sources in a list of references. Use specific evidence from the case and apply appropriate concepts, theories, and models discussed in class or in relevant course readings to highlight and explain the key problems [or problem] that you believe must be solved immediately and describe the underlying symptoms and why they are so critical.

Alternative Solutions

This section is where you provide specific, realistic, and evidence-based solutions to the problems you have identified and make recommendations about how to alleviate the underlying symptomatic conditions impacting the organizational setting. For each solution, you must explain why it was chosen and provide clear evidence to support your reasoning. This can include, for example, course readings and class discussions as well as research resources, such as, books, journal articles, research reports, or government documents. In some cases, your professor may encourage you to include personal, anecdotal experiences as evidence to support why you chose a particular solution or set of solutions. Using anecdotal evidence helps promote reflective thinking about the process of determining what qualifies as a core problem and relevant solution .

Throughout this part of the paper, keep in mind the entire array of problems that must be addressed and describe in detail the solutions that might be implemented to resolve these problems.

Recommended Courses of Action

In some case analysis assignments, your professor may ask you to combine the alternative solutions section with your recommended courses of action. However, it is important to know the difference between the two. A solution refers to the answer to a problem. A course of action refers to a procedure or deliberate sequence of activities adopted to proactively confront a situation, often in the context of accomplishing a goal. In this context, proposed courses of action are based on your analysis of alternative solutions. Your description and justification for pursuing each course of action should represent the overall plan for implementing your recommendations.

For each course of action, you need to explain the rationale for your recommendation in a way that confronts challenges, explains risks, and anticipates any counter-arguments from stakeholders. Do this by considering the strengths and weaknesses of each course of action framed in relation to how the action is expected to resolve the core problems presented, the possible ways the action may affect remaining problems, and how the recommended action will be perceived by each stakeholder.

In addition, you should describe the criteria needed to measure how well the implementation of these actions is working and explain which individuals or groups are responsible for ensuring your recommendations are successful. In addition, always consider the law of unintended consequences. Outline difficulties that may arise in implementing each course of action and describe how implementing the proposed courses of action [either individually or collectively] may lead to new problems [both large and small].

Throughout this section, you must consider the costs and benefits of recommending your courses of action in relation to uncertainties or missing information and the negative consequences of success.

The conclusion should be brief and introspective. Unlike a research paper, the conclusion in a case analysis paper does not include a summary of key findings and their significance, a statement about how the study contributed to existing knowledge, or indicate opportunities for future research.

Begin by synthesizing the core problems presented in the case and the relevance of your recommended solutions. This can include an explanation of what you have learned about the case in the context of your answers to the questions provided by your professor. The conclusion is also where you link what you learned from analyzing the case with the course readings or class discussions. This can further demonstrate your understanding of the relationships between the practical case situation and the theoretical and abstract content of assigned readings and other course content.

Problems to Avoid

The literature on case analysis assignments often includes examples of difficulties students have with applying methods of critical analysis and effectively reporting the results of their assessment of the situation. A common reason cited by scholars is that the application of this type of teaching and learning method is limited to applied fields of social and behavioral sciences and, as a result, writing a case analysis paper can be unfamiliar to most students entering college.

After you have drafted your paper, proofread the narrative flow and revise any of these common errors:

• Unnecessary detail in the background section . The background section should highlight the essential elements of the case based on your analysis. Focus on summarizing the facts and highlighting the key factors that become relevant in the other sections of the paper by eliminating any unnecessary information.
• Analysis relies too much on opinion . Your analysis is interpretive, but the narrative must be connected clearly to evidence from the case and any models and theories discussed in class or in course readings. Any positions or arguments you make should be supported by evidence.
• Analysis does not focus on the most important elements of the case . Your paper should provide a thorough overview of the case. However, the analysis should focus on providing evidence about what you identify are the key events, stakeholders, issues, and problems. Emphasize what you identify as the most critical aspects of the case to be developed throughout your analysis. Be thorough but succinct.
• Writing is too descriptive . A paper with too much descriptive information detracts from your analysis of the complexities of the case situation. Questions about what happened, where, when, and by whom should only be included as essential information leading to your examination of questions related to why, how, and for what purpose.
• Inadequate definition of a core problem and associated symptoms . A common error found in case analysis papers is recommending a solution or course of action without adequately defining or demonstrating that you understand the problem. Make sure you have clearly described the problem and its impact and scope within the organizational setting. Ensure that you have adequately described the root causes w hen describing the symptoms of the problem.
• Recommendations lack specificity . Identify any use of vague statements and indeterminate terminology, such as, “A particular experience” or “a large increase to the budget.” These statements cannot be measured and, as a result, there is no way to evaluate their successful implementation. Provide specific data and use direct language in describing recommended actions.
• Unrealistic, exaggerated, or unattainable recommendations . Review your recommendations to ensure that they are based on the situational facts of the case. Your recommended solutions and courses of action must be based on realistic assumptions and fit within the constraints of the situation. Also note that the case scenario has already happened, therefore, any speculation or arguments about what could have occurred if the circumstances were different should be revised or eliminated.

Bee, Lian Song et al. "Business Students' Perspectives on Case Method Coaching for Problem-Based Learning: Impacts on Student Engagement and Learning Performance in Higher Education." Education & Training 64 (2022): 416-432; The Case Analysis . Fred Meijer Center for Writing and Michigan Authors. Grand Valley State University; Georgallis, Panikos and Kayleigh Bruijn. "Sustainability Teaching using Case-Based Debates." Journal of International Education in Business 15 (2022): 147-163; Hawes, Jon M. "Teaching is Not Telling: The Case Method as a Form of Interactive Learning." Journal for Advancement of Marketing Education 5 (Winter 2004): 47-54; Georgallis, Panikos, and Kayleigh Bruijn. "Sustainability Teaching Using Case-based Debates." Journal of International Education in Business 15 (2022): 147-163; .Dean,  Kathy Lund and Charles J. Fornaciari. "How to Create and Use Experiential Case-Based Exercises in a Management Classroom." Journal of Management Education 26 (October 2002): 586-603; Klebba, Joanne M. and Janet G. Hamilton. "Structured Case Analysis: Developing Critical Thinking Skills in a Marketing Case Course." Journal of Marketing Education 29 (August 2007): 132-137, 139; Klein, Norman. "The Case Discussion Method Revisited: Some Questions about Student Skills." Exchange: The Organizational Behavior Teaching Journal 6 (November 1981): 30-32; Mukherjee, Arup. "Effective Use of In-Class Mini Case Analysis for Discovery Learning in an Undergraduate MIS Course." The Journal of Computer Information Systems 40 (Spring 2000): 15-23; Pessoa, Silviaet al. "Scaffolding the Case Analysis in an Organizational Behavior Course: Making Analytical Language Explicit." Journal of Management Education 46 (2022): 226-251: Ramsey, V. J. and L. D. Dodge. "Case Analysis: A Structured Approach." Exchange: The Organizational Behavior Teaching Journal 6 (November 1981): 27-29; Schweitzer, Karen. "How to Write and Format a Business Case Study." ThoughtCo. https://www.thoughtco.com/how-to-write-and-format-a-business-case-study-466324 (accessed December 5, 2022); Reddy, C. D. "Teaching Research Methodology: Everything's a Case." Electronic Journal of Business Research Methods 18 (December 2020): 178-188; Volpe, Guglielmo. "Case Teaching in Economics: History, Practice and Evidence." Cogent Economics and Finance 3 (December 2015). doi:https://doi.org/10.1080/23322039.2015.1120977.

Writing Tip

Ca se Study and Case Analysis Are Not the Same!

Confusion often exists between what it means to write a paper that uses a case study research design and writing a paper that analyzes a case; they are two different types of approaches to learning in the social and behavioral sciences. Professors as well as educational researchers contribute to this confusion because they often use the term "case study" when describing the subject of analysis for a case analysis paper. But you are not studying a case for the purpose of generating a comprehensive, multi-faceted understanding of a research problem. R ather, you are critically analyzing a specific scenario to argue logically for recommended solutions and courses of action that lead to optimal outcomes applicable to professional practice.

To avoid any confusion, here are twelve characteristics that delineate the differences between writing a paper using the case study research method and writing a case analysis paper:

• Case study is a method of in-depth research and rigorous inquiry ; case analysis is a reliable method of teaching and learning . A case study is a modality of research that investigates a phenomenon for the purpose of creating new knowledge, solving a problem, or testing a hypothesis using empirical evidence derived from the case being studied. Often, the results are used to generalize about a larger population or within a wider context. The writing adheres to the traditional standards of a scholarly research study. A case analysis is a pedagogical tool used to teach students how to reflect and think critically about a practical, real-life problem in an organizational setting.
• The researcher is responsible for identifying the case to study; a case analysis is assigned by your professor . As the researcher, you choose the case study to investigate in support of obtaining new knowledge and understanding about the research problem. The case in a case analysis assignment is almost always provided, and sometimes written, by your professor and either given to every student in class to analyze individually or to a small group of students, or students select a case to analyze from a predetermined list.
• A case study is indeterminate and boundless; a case analysis is predetermined and confined . A case study can be almost anything [see item 9 below] as long as it relates directly to examining the research problem. This relationship is the only limit to what a researcher can choose as the subject of their case study. The content of a case analysis is determined by your professor and its parameters are well-defined and limited to elucidating insights of practical value applied to practice.
• Case study is fact-based and describes actual events or situations; case analysis can be entirely fictional or adapted from an actual situation . The entire content of a case study must be grounded in reality to be a valid subject of investigation in an empirical research study. A case analysis only needs to set the stage for critically examining a situation in practice and, therefore, can be entirely fictional or adapted, all or in-part, from an actual situation.
• Research using a case study method must adhere to principles of intellectual honesty and academic integrity; a case analysis scenario can include misleading or false information . A case study paper must report research objectively and factually to ensure that any findings are understood to be logically correct and trustworthy. A case analysis scenario may include misleading or false information intended to deliberately distract from the central issues of the case. The purpose is to teach students how to sort through conflicting or useless information in order to come up with the preferred solution. Any use of misleading or false information in academic research is considered unethical.
• Case study is linked to a research problem; case analysis is linked to a practical situation or scenario . In the social sciences, the subject of an investigation is most often framed as a problem that must be researched in order to generate new knowledge leading to a solution. Case analysis narratives are grounded in real life scenarios for the purpose of examining the realities of decision-making behavior and processes within organizational settings. A case analysis assignments include a problem or set of problems to be analyzed. However, the goal is centered around the act of identifying and evaluating courses of action leading to best possible outcomes.
• The purpose of a case study is to create new knowledge through research; the purpose of a case analysis is to teach new understanding . Case studies are a choice of methodological design intended to create new knowledge about resolving a research problem. A case analysis is a mode of teaching and learning intended to create new understanding and an awareness of uncertainty applied to practice through acts of critical thinking and reflection.
• A case study seeks to identify the best possible solution to a research problem; case analysis can have an indeterminate set of solutions or outcomes . Your role in studying a case is to discover the most logical, evidence-based ways to address a research problem. A case analysis assignment rarely has a single correct answer because one of the goals is to force students to confront the real life dynamics of uncertainly, ambiguity, and missing or conflicting information within professional practice. Under these conditions, a perfect outcome or solution almost never exists.
• Case study is unbounded and relies on gathering external information; case analysis is a self-contained subject of analysis . The scope of a case study chosen as a method of research is bounded. However, the researcher is free to gather whatever information and data is necessary to investigate its relevance to understanding the research problem. For a case analysis assignment, your professor will often ask you to examine solutions or recommended courses of action based solely on facts and information from the case.
• Case study can be a person, place, object, issue, event, condition, or phenomenon; a case analysis is a carefully constructed synopsis of events, situations, and behaviors . The research problem dictates the type of case being studied and, therefore, the design can encompass almost anything tangible as long as it fulfills the objective of generating new knowledge and understanding. A case analysis is in the form of a narrative containing descriptions of facts, situations, processes, rules, and behaviors within a particular setting and under a specific set of circumstances.
• Case study can represent an open-ended subject of inquiry; a case analysis is a narrative about something that has happened in the past . A case study is not restricted by time and can encompass an event or issue with no temporal limit or end. For example, the current war in Ukraine can be used as a case study of how medical personnel help civilians during a large military conflict, even though circumstances around this event are still evolving. A case analysis can be used to elicit critical thinking about current or future situations in practice, but the case itself is a narrative about something finite and that has taken place in the past.
• Multiple case studies can be used in a research study; case analysis involves examining a single scenario . Case study research can use two or more cases to examine a problem, often for the purpose of conducting a comparative investigation intended to discover hidden relationships, document emerging trends, or determine variations among different examples. A case analysis assignment typically describes a stand-alone, self-contained situation and any comparisons among cases are conducted during in-class discussions and/or student presentations.

The Case Analysis . Fred Meijer Center for Writing and Michigan Authors. Grand Valley State University; Mills, Albert J. , Gabrielle Durepos, and Eiden Wiebe, editors. Encyclopedia of Case Study Research . Thousand Oaks, CA: SAGE Publications, 2010; Ramsey, V. J. and L. D. Dodge. "Case Analysis: A Structured Approach." Exchange: The Organizational Behavior Teaching Journal 6 (November 1981): 27-29; Yin, Robert K. Case Study Research and Applications: Design and Methods . 6th edition. Thousand Oaks, CA: Sage, 2017; Crowe, Sarah et al. “The Case Study Approach.” BMC Medical Research Methodology 11 (2011):  doi: 10.1186/1471-2288-11-100; Yin, Robert K. Case Study Research: Design and Methods . 4th edition. Thousand Oaks, CA: Sage Publishing; 1994.

• << Previous: Reviewing Collected Works
• Next: Writing a Case Study >>
• Last Updated: Mar 6, 2024 1:00 PM
• URL: https://libguides.usc.edu/writingguide/assignments

An official website of the United States government

The .gov means it’s official. Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

The site is secure. The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

• Publications
• Account settings

Preview improvements coming to the PMC website in October 2024. Learn More or Try it out now .

• Advanced Search
• Journal List
• Am J Pharm Educ
• v.84(1); 2020 Jan

Demystifying Content Analysis

A. j. kleinheksel.

a The Medical College of Georgia at Augusta University, Augusta, Georgia

Nicole Rockich-Winston

Huda tawfik.

b Central Michigan University, College of Medicine, Mt. Pleasant, Michigan

Tasha R. Wyatt

Objective. In the course of daily teaching responsibilities, pharmacy educators collect rich data that can provide valuable insight into student learning. This article describes the qualitative data analysis method of content analysis, which can be useful to pharmacy educators because of its application in the investigation of a wide variety of data sources, including textual, visual, and audio files.

Findings. Both manifest and latent content analysis approaches are described, with several examples used to illustrate the processes. This article also offers insights into the variety of relevant terms and visualizations found in the content analysis literature. Finally, common threats to the reliability and validity of content analysis are discussed, along with suitable strategies to mitigate these risks during analysis.

Summary. This review of content analysis as a qualitative data analysis method will provide clarity and actionable instruction for both novice and experienced pharmacy education researchers.

INTRODUCTION

The Academy’s growing interest in qualitative research indicates an important shift in the field’s scientific paradigm. Whereas health science researchers have historically looked to quantitative methods to answer their questions, this shift signals that a purely positivist, objective approach is no longer sufficient to answer pharmacy education’s research questions. Educators who want to study their teaching and students’ learning will find content analysis an easily accessible, robust method of qualitative data analysis that can yield rigorous results for both publication and the improvement of their educational practice. Content analysis is a method designed to identify and interpret meaning in recorded forms of communication by isolating small pieces of the data that represent salient concepts and then applying or creating a framework to organize the pieces in a way that can be used to describe or explain a phenomenon. 1 Content analysis is particularly useful in situations where there is a large amount of unanalyzed textual data, such as those many pharmacy educators have already collected as part of their teaching practice. Because of its accessibility, content analysis is also an appropriate qualitative method for pharmacy educators with limited experience in educational research. This article will introduce and illustrate the process of content analysis as a way to analyze existing data, but also as an approach that may lead pharmacy educators to ask new types of research questions.

Content analysis is a well-established data analysis method that has evolved in its treatment of textual data. Content analysis was originally introduced as a strictly quantitative method, recording counts to measure the observed frequency of pre-identified targets in consumer research. 1 However, as the naturalistic qualitative paradigm became more prevalent in social sciences research and researchers became increasingly interested in the way people behave in natural settings, the process of content analysis was adapted into a more interesting and meaningful approach. Content analysis has the potential to be a useful method in pharmacy education because it can help educational researchers develop a deeper understanding of a particular phenomenon by providing structure in a large amount of textual data through a systematic process of interpretation. It also offers potential value because it can help identify problematic areas in student understanding and guide the process of targeted teaching. Several research studies in pharmacy education have used the method of content analysis. 2-7 Two studies in particular offer noteworthy examples: Wallman and colleagues employed manifest content analysis to analyze semi-structured interviews in order to explore what students learn during experiential rotations, 7 while Moser and colleagues adopted latent content analysis to evaluate open-ended survey responses on student perceptions of learning communities. 6 To elaborate on these approaches further, we will describe the two types of qualitative content analysis, manifest and latent, and demonstrate the corresponding analytical processes using examples that illustrate their benefit.

Qualitative Content Analysis

Content analysis rests on the assumption that texts are a rich data source with great potential to reveal valuable information about particular phenomena. 8 It is the process of considering both the participant and context when sorting text into groups of related categories to identify similarities and differences, patterns, and associations, both on the surface and implied within. 9-11 The method is considered high-yield in educational research because it is versatile and can be applied in both qualitative and quantitative studies. 12 While it is important to note that content analysis has application in visual and auditory artifacts (eg, an image or song), for our purposes we will largely focus on the most common application, which is the analysis of textual or transcribed content (eg, open-ended survey responses, print media, interviews, recorded observations, etc). The terminology of content analysis can vary throughout quantitative and qualitative literature, which may lead to some confusion among both novice and experienced researchers. However, there are also several agreed-upon terms and phrases that span the literature, as found in Table 1 .

Terms and Definitions Used in Qualitative Content Analysis

There is more often disagreement on terminology in the methodological approaches to content analysis, though the most common differentiation is between the two types of content: manifest and latent. In much of the literature, manifest content analysis is defined as describing what is occurring on the surface, what is and literally present, and as “staying close to the text.” 8,13 Manifest content analysis is concerned with data that are easily observable both to researchers and the coders who assist in their analyses, without the need to discern intent or identify deeper meaning. It is content that can be recognized and counted with little training. Early applications of manifest analysis focused on identifying easily observable targets within text (eg, the number of instances a certain word appears in newspaper articles), film (eg, the occupation of a character), or interpersonal interactions (eg, tracking the number of times a participant blinks during an interview). 14 This application, in which frequency counts are used to understand a phenomenon, reflects a surface-level analysis and assumes there is objective truth in the data that can be revealed with very little interpretation. The number of times a target (ie, code) appears within the text is used as a way to understand its prevalence. Quantitative content analysis is always describing a positivist manifest content analysis, in that the nature of truth is believed to be objective, observable, and measurable. Qualitative research, which favors the researcher’s interpretation of an individual’s experience, may also be used to analyze manifest content. However, the intent of the application is to describe a dynamic reality that cannot be separated from the lived experiences of the researcher. Although qualitative content analysis can be conducted whether knowledge is thought to be innate, acquired, or socially constructed, the purpose of qualitative manifest content analysis is to transcend simple word counts and delve into a deeper examination of the language in order to organize large amounts of text into categories that reflect a shared meaning. 15,16 The practical distinction between quantitative and qualitative manifest content analysis is the intention behind the analysis. The quantitative method seeks to generate a numerical value to either cite prevalence or use in statistical analyses, while the qualitative method seeks to identify a construct or concept within the text using specific words or phrases for substantiation, or to provide a more organized structure to the text being described.

Latent content analysis is most often defined as interpreting what is hidden deep within the text. In this method, the role of the researcher is to discover the implied meaning in participants’ experiences. 8,13 For example, in a transcribed exchange in an office setting, a participant might say to a coworker, “Yeah, here we are…another Monday. So exciting!” The researcher would apply context in order to discover the emotion being conveyed (ie, the implied meaning). In this example, the comment could be interpreted as genuine, it could be interpreted as a sarcastic comment made in an attempt at humor in order to develop or sustain social bonds with the coworker, or the context might imply that the sarcasm was meant to convey displeasure and end the interaction.

Latent content analysis acknowledges that the researcher is intimately involved in the analytical process and that the their role is to actively use mental schema, theories, and lenses to interpret and understand the data. 10 Whereas manifest analyses are typically conducted in a way that the researcher is thought to maintain distance and separation from the objects of study, latent analyses underscore the importance of the researcher co-creating meaning with the text. 17 Adding nuance to this type of content, Potter and Levine‐Donnerstein argue that within latent content analysis, there are two distinct types: latent pattern and latent projective . 14 Latent pattern content analysis seeks to establish a pattern of characteristics in the text itself, while latent projective content analysis leverages the researcher’s own interpretations of the meaning of the text. While both approaches rely on codes that emerge from the content using the coder’s own perspectives and mental schema, the distinction between these two types of analyses are in their foci. 14 Though we do not agree, some researchers believe that all qualitative content analysis is latent content analysis. 11 These disagreements typically occur where there are differences in intent and where there are areas of overlap in the results. For example, both qualitative manifest and latent pattern content analyses may identify patterns as a result of their application. Though in their research design, the researcher would have approached the content with different methodological approaches, with a manifest approach seeking only to describe what is observed, and the latent pattern approach seeking to discover an unseen pattern. At this point, these distinctions may seem too philosophical to serve a practical purpose, so we will attempt to clarify these concepts by presenting three types of analyses for illustrative purposes, beginning with a description of how codes are created and used.

Creating and Using Codes

Codes are the currency of content analysis. Researchers use codes to organize and understand their data. Through the coding process, pharmacy educators can systematically and rigorously categorize and interpret vast amounts of text for use in their educational practice or in publication. Codes themselves are short, descriptive labels that symbolically assign a summative or salient attribute to more than one unit of meaning identified in the text. 18 To create codes, a researcher must first become immersed in the data, which typically occurs when a researcher transcribes recorded data or conducts several readings of the text. This process allows the researcher to become familiar with the scope of the data, which spurs nascent ideas about potential concepts or constructs that may exist within it. If studying a phenomenon that has already been described through an existing framework, codes can be created a priori using theoretical frameworks or concepts identified in the literature. If there is no existing framework to apply, codes can emerge during the analytical process. However, emergent codes can also be created as addenda to a priori codes that were identified before the analysis begins if the a priori codes do not sufficiently capture the researcher’s area of interest.

The process of detecting emergent codes begins with identification of units of meaning. While there is no one way to decide what qualifies as a meaning unit, researchers typically define units of meaning differently depending on what kind of analysis is being conducted. As a general rule, when dialogue is being analyzed, such as interviews or focus groups, meaning units are identified as conversational turns, though a code can be as short as one or two words. In written text, such as student reflections or course evaluation data, the researcher must decide if the text should be divided into phrases or sentences, or remain as paragraphs. This decision is usually made based on how many different units of meaning are expressed in a block of text. For example, in a paragraph, if there are several thoughts or concepts being expressed, it is best to break up the paragraph into sentences. If one sentence contains multiple ideas of interest, making it difficult to separate one important thought or behavior from another, then the sentence can be divided into smaller units, such as phrases or sentence fragments. These phrases or sentence fragments are then coded as separate meaning units. Conversely, longer or more complex units of meaning should be condensed into shorter representations that still retain the original meaning in order to reduce the cognitive burden of the analytical process. This could entail removing verbal ticks (eg, “well, uhm…”) from transcribed data or simplifying a compound sentence. Condensation does not ascribe interpretation or implied meaning to a unit, but only shortens a meaning unit as much as possible while preserving the original meaning identified. 18 After condensation, a researcher can proceed to the creation of codes.

Many researchers begin their analyses with several general codes in mind that help guide their focus as defined by their research question, even in instances where the researcher has no a priori model or theory. For example, if a group of instructors are interested in examining recorded videos of their lectures to identify moments of student engagement, they may begin with using generally agreed upon concepts of engagement as codes, such as students “raising their hands,” “taking notes,” and “speaking in class.” However, as the instructors continue to watch their videos, they may notice other behaviors which were not initially anticipated. Perhaps students were seen creating flow charts based on information presented in class. Alternatively, perhaps instructors wanted to include moments when students posed questions to their peers without being prompted. In this case, the instructors would allow the codes of “creating graphic organizers” and “questioning peers” to emerge as additional ways to identify the behavior of student engagement.

Once a researcher has identified condensed units of meaning and labeled them with codes, the codes are then sorted into categories which can help provide more structure to the data. In the above example of recorded lectures, perhaps the category of “verbal behaviors” could be used to group the codes of “speaking in class” and “questioning peers.” For complex analyses, subcategories can also be used to better organize a large amount of codes, but solely at the discretion of the researcher. Two or more categories of codes are then used to identify or support a broader underlying meaning which develops into themes. Themes are most often employed in latent analyses; however, they are appropriate in manifest analyses as well. Themes describe behaviors, experiences, or emotions that occur throughout several categories. 18 Figure 1 illustrates this process. Using the same videotaped lecture example, the instructors might identify two themes of student engagement, “active engagement” and “passive engagement,” where active engagement is supported by the category of “verbal behavior” and also a category that includes the code of “raising their hands” (perhaps something along the lines of “pursuing engagement”), and the theme of “passive engagement” is supported by a category used to organize the behaviors of “taking notes” and “creating graphic organizers.”

The Process of Qualitative Content Analysis

To more fully demonstrate the process of content analysis and the generation and use of codes, categories, and themes, we present and describe examples of both manifest and latent content analysis. Given that there are multiple ways to create and use codes, our examples illustrate both processes of creating and using a predetermined set of codes. Regardless of the kind of content analysis instructors want to conduct, the initial steps are the same. The instructor must analyze the data using codes as a sense-making process.

Manifest Content Analysis

The first form of analysis, manifest content analysis, examines text for elements that exist on the surface of the text, the meaning of which is taken at face value. Schools and colleges of pharmacy may benefit from conducting manifest content analyses at a programmatic level, including analysis of student evaluations to determine the value of certain courses, or analysis of recruitment materials for addressing issues of cultural humility in a uniform manner. Such uses for manifest content analysis may help administrators make more data-based decisions about students and courses. However, for our example of manifest content analysis, we illustrate the use of content analysis in informing instruction for a single pharmacy educator ( Figure 2 ).

A Student’s Completed Beta-blocker Case with Codes in Underlined Bold Text

In the example, a pharmacology instructor is trying to assess students’ understanding of three concepts related to the beta-blocker class of drugs: indication of the drug, relevance of family history, and contraindications and precautions. To do so, the instructor asks the students to write a patient case in which beta-blockers are indicated. The instructor gives the students the following prompt: “Reverse-engineer a case in which beta-blockers would be prescribed to the patient. Include a history of the present illness, the patients’ medical, family, and social history, medications, allergies, and relevant lab tests.” Figure 2 is a hypothetical student’s completed assignment, in which they demonstrate their understanding of when and why a beta-blocker would be prescribed.

The student-generated cases are then treated as data and analyzed for the presence of the three previously identified indicators of understanding in order to help the instructor make decisions about where and how to focus future teaching efforts related to this drug class. Codes are created a priori out of the instructor’s interest in analyzing students’ understanding of the concepts related to beta-blocker prescriptions. A codebook ( Table 2 ) is created with the following columns: name of code, code description, and examples of the code. This codebook helps an individual researcher to approach their analysis systematically, but it can also facilitate coding by multiple coders who would apply the same rules outlined in the codebook to the coding process.

Example Code Book Created for Manifest Content Analysis

Using multiple coders introduces complexity to the analysis process, but it is oftentimes the only practical way to analyze large amounts of data. To ensure that all coders are working in tandem, they must establish inter-rater reliability as part of their training process. This process requires that a single form of text be selected, such as one student evaluation. After reviewing the codebook and receiving instruction, everyone on the team individually codes the same piece of data. While calculating percentage agreement has sometimes been used to establish inter-rater reliability, most publication editors require more rigorous statistical analysis (eg, Krippendorf’s alpha, or Cohen’s kappa). 19 Detailed descriptions of these statistics fall outside the scope of this introduction, but it is important to note that the choice depends on the number of coders, the sample size, and the type of data to be analyzed.

Latent Content Analysis

Latent content analysis is another option for pharmacy educators, especially when there are theoretical frameworks or lenses the educator proposes to apply. Such frameworks describe and provide structure to complex concepts and may often be derived from relevant theories. Latent content analysis requires that the researcher is intimately involved in interpreting and finding meaning in the text because meaning is not readily apparent on the surface. 10 To illustrate a latent content analysis using a combination of a priori and emergent codes, we will use the example of a transcribed video excerpt from a student pharmacist interaction with a standardized patient. In this example, the goal is for first-year students to practice talking to a customer about an over-the-counter medication. The case is designed to simulate a customer at a pharmacy counter, who is seeking advice on a medication. The learning objectives for the pharmacist in-training are to assess the customer’s symptoms, determine if the customer can self-treat or if they need to seek out their primary care physician, and then prescribe a medication to alleviate the patient’s symptoms.

To begin, pharmacy educators conducting educational research should first identify what they are looking for in the video transcript. In this case, because the primary outcome for this exercise is aimed at assessing the “soft skills” of student pharmacists, codes are created using the counseling rubric created by Horton and colleagues. 20 Four a priori codes are developed using the literature: empathy, patient-friendly terms, politeness, and positive attitude. However, because the original four codes are inadequate to capture all areas representing the skills the instructor is looking for during the process of analysis, four additional codes are also created: active listening, confidence, follow-up, and patient at ease. Figure 3 presents the video transcript with each of the codes assigned to the meaning units in bolded parentheses.

A Transcript of a Student’s (JR) Experience with a Standardized Patient (SP) in Which the Codes are Bolded in Parentheses

Following the initial coding using these eight codes, the codes are consolidated to create categories, which are depicted in the taxonomy in Figure 4 . Categories are relationships between codes that represent a higher level of abstraction in the data. 18 To reach conclusions and interpret the fundamental underlying meaning in the data, categories are then organized into themes ( Figure 1 ). Once the data are analyzed, the instructor can assign value to the student’s performance. In this case, the coding process determines that the exercise demonstrated both positive and negative elements of communication and professionalism. Under the category of professionalism, the student generally demonstrated politeness and a positive attitude toward the standardized patient, indicating to the reviewer that the theme of perceived professionalism was apparent during the encounter. However, there were several instances in which confidence and appropriate follow-up were absent. Thus, from a reviewer perspective, the student's performance could be perceived as indicating an opportunity to grow and improve as a future professional. Typically, there are multiple codes in a category and multiple categories in a theme. However, as seen in the example taxonomy, this is not always the case.

Example of a Latent Content Analysis Taxonomy

If the educator is interested in conducting a latent projective analysis, after identifying the construct of “soft skills,” the researcher allows for each coder to apply their own mental schema as they look for positive and negative indicators of the non-technical skills they believe a student should develop. Mental schema are the cognitive structures that provide organization to knowledge, which in this case allows coders to categorize the data in ways that fit their existing understanding of the construct. The coders will use their own judgement to identify the codes they feel are relevant. The researcher could also choose to apply a theoretical lens to more effectively conceptualize the construct of “soft skills,” such as Rogers' humanism theory, and more specifically, concepts underlying his client-centered therapy. 21 The role of theory in both latent pattern and latent projective analyses is at the discretion of the researcher, and often is determined by what already exists in the literature related to the research question. Though, typically, in latent pattern analyses theory is used for deductive coding, and in latent projective analyses underdeveloped theory is used to first deduce codes and then for induction of the results to strengthen the theory applied. For our example, Rogers describes three salient qualities to develop and maintain a positive client-professional relationship: unconditional positive regard, genuineness, and empathetic understanding. 21 For the third element, specifically, the educator could look for units of meaning that imply empathy and active listening. For our video transcript analysis, this is evident when the student pharmacist demonstrated empathy by responding, "Yeah, I understand," when discussing aggravating factors for the patient's condition. The outcome for both latent pattern and latent projective content analysis is to discover the underlying meaning in a text, such as social rules or mental models. In this example, both pattern and projective approaches can discover interpreted aspects of a student’s abilities and mental models for constructs such as professionalism and empathy. The difference in the approaches is where the precedence lies: in the belief that a pattern is recognizable in the content, or in the mental schema and lived experiences of the coder(s). To better illustrate the differences in the processes of latent pattern and projective content analyses, Figure 5 presents a general outline of each method beginning with the creation of codes and concluding with the generation of themes.

Flow Chart of the Stages of Latent Pattern and Latent Projective Content Analysis

How to Choose a Methodological Approach to Content Analysis

To determine which approach a researcher should take in their content analysis, two decisions need to be made. First, researchers must determine their goal for the analysis. Second, the researcher must decide where they believe meaning is located. 14 If meaning is located in the discrete elements of the content that are easily identified on the surface of the text, then manifest content analysis is appropriate. If meaning is located deep within the content and the researcher plans to discover context cues and make judgements about implied meaning, then latent content analysis should be applied. When designing the latent content analysis, a researcher then must also identify their focus. If the analysis is intended to identify a recognizable truth within the content by uncovering connections and characteristics that all coders should be able to discover, then latent pattern content analysis is appropriate. If, on the other hand, the researcher will rely heavily on the judgment of the coders and believes that interpretation of the content must leverage the mental schema of the coders to locate deeper meaning, then latent projective content analysis is the best choice.

To demonstrate how a researcher might choose a methodological approach, we have presented a third example of data in Figure 6 . In our two previous examples of content analysis, we used student data. However, faculty data can also be analyzed as part of educational research or for faculty members to improve their own teaching practices. Recall in the video data analyzed using latent content analysis, the student was tasked to identify a suitable over-the-counter medication for a patient complaining of heartburn symptoms. We have extended this example by including an interview with the pharmacy educator supervising the student who was videotaped. The goal of the interview is to evaluate the educator’s ability to assess the student’s performance with the standardized patient. Figure 6 is an excerpt of the interview between the course instructor and an instructional coach. In this conversation, the instructional coach is eliciting evidence to support the faculty member’s views, judgements, and rationale for the educator’s evaluation of the student’s performance.

A Transcript of an Interview in Which the Interviewer (IN) Questions a Faculty Member (FM) Regarding Their Student’s Standardized Patient Experience

Manifest content analysis would be a valid choice for this data if the researcher was looking to identify evidence of the construct of “instructor priorities” and defined discrete codes that described aspects of performance such as “communication,” “referrals,” or “accurate information.” These codes could be easily identified on the surface of the transcribed interview by identifying keywords related to each code, such as “communicate,” “talk,” and “laugh,” for the code of “communication.” This would allow coders to identify evidence of the concept of “instructor priorities” by sorting through a potentially large amount of text with predetermined targets in mind.

To conduct a latent pattern analysis of this interview, researchers would first immerse themselves in the data to identify a theoretical framework or concepts that represent the area of interest so that coders could discover an emerging truth underneath the surface of the data. After immersion in the data, a researcher might believe it would be interesting to more closely examine the strategies the coach uses to establish rapport with the instructor as a way to better understand models of professional development. These strategies could not be easily identified in the transcripts if read literally, but by looking for connections within the text, codes related to instructional coaching tactics emerge. A latent pattern analysis would require that the researcher code the data in a way that looks for patterns, such as a code of “facilitating reflection,” that could be identified in open-ended questions and other units of meaning where the coder saw evidence of probing techniques, or a code of “establishing rapport” for which a coder could identify nonverbal cues such as “[IN leans forward in chair].”

Conducting latent projective content analysis might be useful if the researcher was interested in using a broader theoretical lens, such as Mezirow’s theory of transformative learning. 22 In this example, the faculty member is understood to have attempted to change a learner’s frame of reference by facilitating cognitive dissonance or a disorienting experience through a standardized patient simulation. To conduct a latent projective analysis, the researcher could analyze the faculty member’s interview using concepts found in this theory. This kind of analysis will help the researcher assess the level of change that the faculty member was able to perceive, or expected to witness, in their attempt to help their pharmacy students improve their interactions with patients. The units of meaning and subsequent codes would rely on the coders to apply their own knowledge of transformative learning because of the absence in the theory of concrete, context-specific behaviors to identify. For this analysis, the researcher would rely on their interpretations of what challenging educational situations look like, what constitutes cognitive dissonance, or what the faculty member is really expecting from his students’ performance. The subsequent analysis could provide evidence to support the use of such standardized patient encounters within the curriculum as a transformative learning experience and would also allow the educator to self-reflect on his ability to assess simulated activities.

OTHER ASPECTS TO CONSIDER

Navigating terminology.

Among the methodological approaches, there are other terms for content analysis that researchers may come across. Hsieh and Shannon 10 proposed three qualitative approaches to content analysis: conventional, directed, and summative. These categories were intended to explain the role of theory in the analysis process. In conventional content analysis, the researcher does not use preconceived categories because existing theory or literature are limited. In directed content analysis, the researcher attempts to further describe a phenomenon already addressed by theory, applying a deductive approach and using identified concepts or codes from exiting research to validate the theory. In summative content analysis, a descriptive approach is taken, identifying and quantifying words or content in order to describe their context. These three categories roughly map to the terms of latent projective, latent pattern, and manifest content analyses respectively, though not precisely enough to suggest that they are synonyms.

Graneheim and colleagues 9 reference the inductive, deductive, and abductive methods of interpretation of content analysis, which are data-driven, concept-driven, and fluid between both data and concepts, respectively. Where manifest content produces phenomenological descriptions most often (but not always) through deductive interpretation, and latent content analysis produces interpretations most often (but not always) through inductive or abductive interpretations. Erlingsson and Brysiewicz 23 refer to content analysis as a continuum, progressing as the researcher develops codes, then categories, and then themes. We present these alternative conceptualizations of content analysis to illustrate that the literature on content analysis, while incredibly useful, presents a multitude of interpretations of the method itself. However, these complexities should not dissuade readers from using content analysis. Identifying what you want to know (ie, your research question) will effectively direct you toward your methodological approach. That said, we have found the most helpful aid in learning content analysis is the application of the methods we have presented.

Ensuring Quality

The standards used to evaluate quantitative research are seldom used in qualitative research. The terms “reliability” and “validity” are typically not used because they reflect the positivist quantitative paradigm. In qualitative research, the preferred term is “trustworthiness,” which is comprised of the concepts of credibility, transferability, dependability, and confirmability, and researchers can take steps in their work to demonstrate that they are trustworthy. 24 Though establishing trustworthiness is outside the scope of this article, novice researchers should be familiar with the necessary steps before publishing their work. This suggestion includes exploration of the concept of saturation, the idea that researchers must demonstrate they have collected and analyzed enough data to warrant their conclusions, which has been a focus of recent debate in qualitative research. 25

There are several threats to the trustworthiness of content analysis in particular. 14 We will use the terms “reliability and validity” to describe these threats, as they are conceptualized this way in the formative literature, and it may be easier for researchers with a quantitative research background to recognize them. Though some of these threats may be particular to the type of data being analyzed, in general, there are risks specific to the different methods of content analysis. In manifest content analysis, reliability is necessary but not sufficient to establish validity. 14 Because there is little judgment required of the coders, lack of high inter-rater agreement among coders will render the data invalid. 14 Additionally, coder fatigue is a common threat to manifest content analysis because the coding is clerical and repetitive in nature.

For latent pattern content analysis, validity and reliability are inversely related. 14 Greater reliability is achieved through more detailed coding rules to improve consistency, but these rules may diminish the accessibility of the coding to consumers of the research. This is defined as low ecological validity. Higher ecological validity is achieved through greater reliance on coder judgment to increase the resonance of the results with the audience, yet this often decreases the inter-rater reliability. In latent projective content analysis, reliability and validity are equivalent. 14 Consistent interpretations among coders both establishes and validates the constructed norm; construction of an accurate norm is evidence of consistency. However, because of this equivalence, issues with low validity or low reliability cannot be isolated. A lack of consistency may result from coding rules, lack of a shared schema, or issues with a defined variable. Reasons for low validity cannot be isolated, but will always result in low consistency.

Any good analysis starts with a codebook and coder training. It is important for all coders to share the mental model of the skill, construct, or phenomenon being coded in the data. However, when conducting latent pattern or projective content analysis in particular, micro-level rules and definitions of codes increase the threat of ecological validity, so it is important to leave enough room in the codebook and during the training to allow for a shared mental schema to emerge in the larger group rather than being strictly directed by the lead researcher. Stability is another threat, which occurs when coders make different judgments as time passes. To reduce this risk, allowing for recoding at a later date can increase the consistency and stability of the codes. Reproducibility is not typically a goal of qualitative research, 15 but for content analysis, codes that are defined both prior to and during analysis should retain their meaning. Researchers can increase the reproducibility of their codebook by creating a detailed audit trail, including descriptions of the methods used to create and define the codes, materials used for the training of the coders, and steps taken to ensure inter-rater reliability.

In all forms of qualitative analysis, coder fatigue is a common threat to trustworthiness, even when the instructor is coding individually. Over time, the cases may start to look the same, making it difficult to refocus and look at each case with fresh eyes. To guard against this, coders should maintain a reflective journal and write analytical memos to help stay focused. Memos might include insights that the researcher has, such as patterns of misunderstanding, areas to focus on when considering re-teaching specific concepts, or specific conversations to have with students. Fatigue can also be mitigated by occasionally talking to participants (eg, meeting with students and listening for their rationale on why they included specific pieces of information in an assignment). These are just examples of potential exercises that can help coders mitigate cognitive fatigue. Most researchers develop their own ways to prevent the fatigue that can seep in after long hours of looking at data. But above all, a sufficient amount of time should be allowed for analysis, so that coders do not feel rushed, and regular breaks should be scheduled and enforced.

Qualitative content analysis is both accessible and high-yield for pharmacy educators and researchers. Though some of the methods may seem abstract or fluid, the nature of qualitative content analysis encompasses these concerns by providing a systematic approach to discover meaning in textual data, both on the surface and implied beneath it. As with most research methods, the surest path towards proficiency is through application and intentional, repeated practice. We encourage pharmacy educators to ask questions suited for qualitative research and to consider the use of content analysis as a qualitative research method for discovering meaning in their data.

A three-level framework for affective content analysis and its case studies

• Published: 28 March 2012
• Volume 70 , pages 757–779, ( 2014 )

Cite this article

• Min Xu 1 , 2 ,
• Jinqiao Wang 2 ,
• Xiangjian He 1 ,
• Jesse S. Jin 3 ,
• Suhuai Luo 3 &
• Hanqing Lu 2  

906 Accesses

27 Citations

Explore all metrics

Emotional factors directly reflect audiences’ attention, evaluation and memory. Recently, video affective content analysis attracts more and more research efforts. Most of the existing methods map low-level affective features directly to emotions by applying machine learning. Compared to human perception process, there is actually a gap between low-level features and high-level human perception of emotion. In order to bridge the gap, we propose a three-level affective content analysis framework by introducing mid-level representation to indicate dialog, audio emotional events (e.g., horror sounds and laughters) and textual concepts (e.g., informative keywords). Mid-level representation is obtained from machine learning on low-level features and used to infer high-level affective content. We further apply the proposed framework and focus on a number of case studies. Audio emotional event, dialog and subtitle are studied to assist affective content detection in different video domains/genres. Multiple modalities are considered for affective analysis, since different modality has its own merit to evoke emotions. Experimental results shows the proposed framework is effective and efficient for affective content analysis. Audio emotional event, dialog and subtitle are promising mid-level representations.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Price includes VAT (Russian Federation)

Instant access to the full article PDF.

Rent this article via DeepDyve

Institutional subscriptions

Similar content being viewed by others

Context-Aware Multimodal Emotion Recognition

Multi-modal learning for affective content analysis in movies.

Yun Yi & Hanli Wang

A Novel Affective Visualization System for Videos Based on Acoustic and Visual Features

Arifin S, Cheung PYK (2006) User attention based arousal content modeling. In: Proceedings of the international conference on image processing, pp 433–436

Arifin S, Cheung PYK (2007) A computation method for video segmentation utilizing the pleasure-arousal-dominance emotional information. In: Proceedings of the ACM multimedia conference, pp 68–77

Berry MW, Drmavc Z, Jessup ER (1999) Matrices, vector spaces, and information retrieval. SIAM Rev 41(2):335–362

Article   MATH   MathSciNet   Google Scholar  

Berry MW, Dumais ST, O’Brien GW (1995) Using linear algebra for intelligent information retrieval. SIAM Rev 37:301–328

Article   MathSciNet   Google Scholar  

Chan C, Jones GJF (2005) Affect-based indexing and retrieval of films. In: Proceedings of the ACM multimedia conference, pp 427–430

Chang CC, Lin CJ (2006) Libsvm – a library for support vector machines. In: http://www.csie.ntu.edu.tw/~cjlin/libsvm/

Chen YH, Kuo JH, Chu WT, Wu JL (2006) Movie emotional event detection based on music mood and video tempo. In: Proceedings of IEEE international conference on consumer electronics, pp 151–152

Frantzidis CA, Bratsas C, Klados M, Konstantinidis E, Lithari CD, Vivas AB, Papadelis CL, Kaldoudi E, Pappas C, Bamidis PD (2010) On the classification of emotional biosignals evoked while viewing affective pictures: an integrated data-mining-based approach for healthcare applications. IEEE Trans Inf Technol Biomed 14(2):309–318

Article   Google Scholar  

Gales M, Woodland P (2006) Recent progress in large vocabulary continuous speech recognition: an htk perspective. In: ICASSP tutorial

Gruhne M, Dittmar C (2009) Comparison of harmonic mid-level representations for genre recognition. In: Proceedings of third international workshop on learning semantics of audio signals, pp 91–102

Hanjalic A (2006) Extracting moods from pictures and sounds: towards truly personalized tv. IEEE Signal Process Mag 23(2):90–100

Hanjalic A, Xu LQ (2005) Affective video content representation and modeling. IEEE Trans Multimedia 7(1):143–154

Irie G, Hidaka K, Satou T, Kojima A, Yamasaki T, Aizawa K (2009) Latent topic driving model for movie affective scene classification. In: Proceedings of the ACM multimedia conference, pp 565–568

Jiang H, Lin T, Zhang HJ (2000) Video segmentation with the assistance of audio content analysis. In: Proceedings of IEEE international conference on multimedia & expo, vol 3, pp 1507–1510

Kang HB (2003) Affective content detection using hmms. In: Proceedings of the ACM multimedia conference, pp 259–262

Kim J, Andre E (2008) Emotion-specific dichotomous classification and feature-level fusion of multichannel biosignals for automatic emotion recognition. In: Proceedings of IEEE international conference on multisensor fusion and integration for intelligent systems, pp 114–118

Kovecses Z (2003) Metaphor and emotion language, culture, and body in human feeling. Cambridge University Press

Machajdik J, Hanbury A (2010) Affective image classification using features inspired by psychology and art theory. In: Proceedings of the ACM international conference on multimedia, pp 83–92

Moncrieff S, Dorai CSV (2001) Affect computing in film through sound energy dynamics. In: Proceedings of the ACM on multimedia conference, pp 525–527

Money AG, Agius H (2010) Elvis: entertainment-led video summaries. ACM T Multim Comput 6(3):1–30

Plantinga C, Smith GM (1999) Passionate views: film, cognition and emotion. The Johns Hopkins University Press

Porter MF (1980) An algorithm for suffix stripping. Program 14(3):130–137

Rasheed Z, Sheikh Y, Shah M (2005) On the use of computable features for film classification. IEEE Trans Circuits Syst Video Technol 15(1):52–64

Sebe N, Cohen I, Gevers T, Huang TS (2006) Emotion recognition based on joint visual and audio cues. In: Proceedings of the 18th international conference on pattern recognition, pp 1136–1139

Smith J (1998) The sounds of commerce: marketing popular film music. Columbia University Press

Soleymani M, Chanel G, Kierkels JJM, Pun T (2008) Affective characterization of movie scenes based on multimedia content analysis and user’s physiological emotional responses. In: Proceedings of 2008 10th IEEE international symposium on multimedia (ISM ’08), pp 228–235

Soleymani M, Kierkels JJM, Chanel G, Pun T (2009) A bayesian framework for video affective representation. In: Proceedings of the international conference on affective computing and intelligent interaction

Wang HL, Cheong LF (2006) Affective understanding in film. IEEE Transactions on Circuits and Systems for Video Technology 16(6):689–704

Xu M, Xu CS, Duan LY, Jin JS, Luo S (2008) Audio keywords generation for sports video analysis. ACM T Multim Comput 4(2):1–23

Xu M, Duan LY, Xu CS, Tian Q (2003) A fusion scheme of visual and auditory modalities for event detection in sports video. In: Proceedings of IEEE international conference on acoustic, speech, and signal processing, vol 3, pp 189–192

Xu M, Duan L, Cai J, Chia LT, Xu C, Tian Q (2004) Hmm-based audio keyword generation. In: Proceedings of IEEE pacific rim conference on multimedia (PCM), pp 566–574

Xu M, Maddage NC, Xu CS, Kankanhalli M, Tian Q (2003) Creating audio keywords for event detection in soccer video. In: Proceedings of international conference on multimedia & expo, vol 2, pp 143–154

Zeng Z, Tu J, Liu M, Huang TS, Pianfetti B, Roth D, Levinson S (2007) Audio-visual affect recognition. IEEE Trans Multimedia 9(6):424–428

Zhang S, Huang Q, Jiang S, Gao W, Tian Q (2010) Affective visualization and retrieval for music video. IEEE Trans Multimedia 12(6):510–522

Download references

Acknowledgements

This research was supported by National Natural Science Foundation of China No. 61003161, No. 60905008 and UTS ECR Grant.

Author information

Authors and affiliations.

Center for Innovation in IT Services and Applications, University of Technology, Sydney, Australia

Min Xu & Xiangjian He

National Laboratory of Pattern Recognition Institute of Automation, Chinese Academy of Sciences, Beijing, China

Min Xu, Jinqiao Wang & Hanqing Lu

School of Design, Communication and IT, University of Newcastle, Callaghan, NSW 2308, Australia

Jesse S. Jin & Suhuai Luo

You can also search for this author in PubMed   Google Scholar

Corresponding authors

Correspondence to Min Xu or Jinqiao Wang .

Rights and permissions

Reprints and permissions

About this article

Xu, M., Wang, J., He, X. et al. A three-level framework for affective content analysis and its case studies. Multimed Tools Appl 70 , 757–779 (2014). https://doi.org/10.1007/s11042-012-1046-8

Download citation

Published : 28 March 2012

Issue Date : May 2014

DOI : https://doi.org/10.1007/s11042-012-1046-8

Share this article

Anyone you share the following link with will be able to read this content:

Sorry, a shareable link is not currently available for this article.

Provided by the Springer Nature SharedIt content-sharing initiative

• Affective content analysis
• Mid-level representation
• Multiple modality
• Find a journal
• Publish with us
• Track your research

• Discounts and promotions
• Delivery and payment

Cart is empty!

Case study definition

Case study, a term which some of you may know from the "Case Study of Vanitas" anime and manga, is a thorough examination of a particular subject, such as a person, group, location, occasion, establishment, phenomena, etc. They are most frequently utilized in research of business, medicine, education and social behaviour. There are a different types of case studies that researchers might use:

• Collective case studies

• Descriptive case studies

• Explanatory case studies

• Exploratory case studies

• Instrumental case studies

• Intrinsic case studies

Case studies are usually much more sophisticated and professional than regular essays and courseworks, as they require a lot of verified data, are research-oriented and not necessarily designed to be read by the general public.

How to write a case study?

It very much depends on the topic of your case study, as a medical case study and a coffee business case study have completely different sources, outlines, target demographics, etc. But just for this example, let's outline a coffee roaster case study. Firstly, it's likely going to be a problem-solving case study, like most in the business and economics field are. Here are some tips for these types of case studies:

• Your case scenario should be precisely defined in terms of your unique assessment criteria.

• Determine the primary issues by analyzing the scenario. Think about how they connect to the main ideas and theories in your piece.

• Find and investigate any theories or methods that might be relevant to your case.

• Keep your audience in mind. Exactly who are your stakeholder(s)? If writing a case study on coffee roasters, it's probably gonna be suppliers, landlords, investors, customers, etc.

• Indicate the best solution(s) and how they should be implemented. Make sure your suggestions are grounded in pertinent theories and useful resources, as well as being realistic, practical, and attainable.

• Carefully proofread your case study. Keep in mind these four principles when editing: clarity, honesty, reality and relevance.

Are there any online services that could write a case study for me?

Luckily, there are!

We completely understand and have been ourselves in a position, where we couldn't wrap our head around how to write an effective and useful case study, but don't fear - our service is here.

We are a group that specializes in writing all kinds of case studies and other projects for academic customers and business clients who require assistance with its creation. We require our writers to have a degree in your topic and carefully interview them before they can join our team, as we try to ensure quality above all. We cover a great range of topics, offer perfect quality work, always deliver on time and aim to leave our customers completely satisfied with what they ordered.

The ordering process is fully online, and it goes as follows:

• Select the topic and the deadline of your case study.

• Provide us with any details, requirements, statements that should be emphasized or particular parts of the writing process you struggle with.

• Leave the email address, where your completed order will be sent to.

• Select your payment type, sit back and relax!

With lots of experience on the market, professionally degreed writers, online 24/7 customer support and incredibly low prices, you won't find a service offering a better deal than ours.

Data Analytics Case Study Guide 2024

by Sam McKay, CFA | Data Analytics

Data analytics case studies reveal how businesses harness data for informed decisions and growth.

For aspiring data professionals, mastering the case study process will enhance your skills and increase your career prospects.

So, how do you approach a case study?

Use these steps to process a data analytics case study:

Understand the Problem: Grasp the core problem or question addressed in the case study.

Collect Relevant Data: Gather data from diverse sources, ensuring accuracy and completeness.

Apply Analytical Techniques: Use appropriate methods aligned with the problem statement.

Visualize Insights: Utilize visual aids to showcase patterns and key findings.

Derive Actionable Insights: Focus on deriving meaningful actions from the analysis.

This article will give you detailed steps to navigate a case study effectively and understand how it works in real-world situations.

By the end of the article, you will be better equipped to approach a data analytics case study, strengthening your analytical prowess and practical application skills.

Let’s dive in!

Table of Contents

What is a Data Analytics Case Study?

A data analytics case study is a real or hypothetical scenario where analytics techniques are applied to solve a specific problem or explore a particular question.

It’s a practical approach that uses data analytics methods, assisting in deciphering data for meaningful insights. This structured method helps individuals or organizations make sense of data effectively.

Additionally, it’s a way to learn by doing, where there’s no single right or wrong answer in how you analyze the data.

So, what are the components of a case study?

Key Components of a Data Analytics Case Study

A data analytics case study comprises essential elements that structure the analytical journey:

Problem Context: A case study begins with a defined problem or question. It provides the context for the data analysis , setting the stage for exploration and investigation.

Data Collection and Sources: It involves gathering relevant data from various sources , ensuring data accuracy, completeness, and relevance to the problem at hand.

Analysis Techniques: Case studies employ different analytical methods, such as statistical analysis, machine learning algorithms, or visualization tools, to derive meaningful conclusions from the collected data.

Insights and Recommendations: The ultimate goal is to extract actionable insights from the analyzed data, offering recommendations or solutions that address the initial problem or question.

Now that you have a better understanding of what a data analytics case study is, let’s talk about why we need and use them.

Why Case Studies are Integral to Data Analytics

Case studies serve as invaluable tools in the realm of data analytics, offering multifaceted benefits that bolster an analyst’s proficiency and impact:

Real-Life Insights and Skill Enhancement: Examining case studies provides practical, real-life examples that expand knowledge and refine skills. These examples offer insights into diverse scenarios, aiding in a data analyst’s growth and expertise development.

Validation and Refinement of Analyses: Case studies demonstrate the effectiveness of data-driven decisions across industries, providing validation for analytical approaches. They showcase how organizations benefit from data analytics. Also, this helps in refining one’s own methodologies

Showcasing Data Impact on Business Outcomes: These studies show how data analytics directly affects business results, like increasing revenue, reducing costs, or delivering other measurable advantages. Understanding these impacts helps articulate the value of data analytics to stakeholders and decision-makers.

Learning from Successes and Failures: By exploring a case study, analysts glean insights from others’ successes and failures, acquiring new strategies and best practices. This learning experience facilitates professional growth and the adoption of innovative approaches within their own data analytics work.

Including case studies in a data analyst’s toolkit helps gain more knowledge, improve skills, and understand how data analytics affects different industries.

Using these real-life examples boosts confidence and success, guiding analysts to make better and more impactful decisions in their organizations.

But not all case studies are the same.

Let’s talk about the different types.

Types of Data Analytics Case Studies

Data analytics encompasses various approaches tailored to different analytical goals:

Exploratory Case Study: These involve delving into new datasets to uncover hidden patterns and relationships, often without a predefined hypothesis. They aim to gain insights and generate hypotheses for further investigation.

Predictive Case Study: These utilize historical data to forecast future trends, behaviors, or outcomes. By applying predictive models, they help anticipate potential scenarios or developments.

Diagnostic Case Study: This type focuses on understanding the root causes or reasons behind specific events or trends observed in the data. It digs deep into the data to provide explanations for occurrences.

Prescriptive Case Study: This case study goes beyond analytics; it provides actionable recommendations or strategies derived from the analyzed data. They guide decision-making processes by suggesting optimal courses of action based on insights gained.

Each type has a specific role in using data to find important insights, helping in decision-making, and solving problems in various situations.

Regardless of the type of case study you encounter, here are some steps to help you process them.

Roadmap to Handling a Data Analysis Case Study

Embarking on a data analytics case study requires a systematic approach, step-by-step, to derive valuable insights effectively.

Here are the steps to help you through the process:

Step 1: Understanding the Case Study Context: Immerse yourself in the intricacies of the case study. Delve into the industry context, understanding its nuances, challenges, and opportunities.

Identify the central problem or question the study aims to address. Clarify the objectives and expected outcomes, ensuring a clear understanding before diving into data analytics.

Step 2: Data Collection and Validation: Gather data from diverse sources relevant to the case study. Prioritize accuracy, completeness, and reliability during data collection. Conduct thorough validation processes to rectify inconsistencies, ensuring high-quality and trustworthy data for subsequent analysis.

Step 3: Problem Definition and Scope: Define the problem statement precisely. Articulate the objectives and limitations that shape the scope of your analysis. Identify influential variables and constraints, providing a focused framework to guide your exploration.

Step 4: Exploratory Data Analysis (EDA): Leverage exploratory techniques to gain initial insights. Visualize data distributions, patterns, and correlations, fostering a deeper understanding of the dataset. These explorations serve as a foundation for more nuanced analysis.

Step 5: Data Preprocessing and Transformation: Cleanse and preprocess the data to eliminate noise, handle missing values, and ensure consistency. Transform data formats or scales as required, preparing the dataset for further analysis.

Step 6: Data Modeling and Method Selection: Select analytical models aligning with the case study’s problem, employing statistical techniques, machine learning algorithms, or tailored predictive models.

In this phase, it’s important to develop data modeling skills. This helps create visuals of complex systems using organized data, which helps solve business problems more effectively.

Understand key data modeling concepts, utilize essential tools like SQL for database interaction, and practice building models from real-world scenarios.

Furthermore, strengthen data cleaning skills for accurate datasets, and stay updated with industry trends to ensure relevance.

Step 7: Model Evaluation and Refinement: Evaluate the performance of applied models rigorously. Iterate and refine models to enhance accuracy and reliability, ensuring alignment with the objectives and expected outcomes.

Step 8: Deriving Insights and Recommendations: Extract actionable insights from the analyzed data. Develop well-structured recommendations or solutions based on the insights uncovered, addressing the core problem or question effectively.

Step 9: Communicating Results Effectively: Present findings, insights, and recommendations clearly and concisely. Utilize visualizations and storytelling techniques to convey complex information compellingly, ensuring comprehension by stakeholders.

Step 10: Reflection and Iteration: Reflect on the entire analysis process and outcomes. Identify potential improvements and lessons learned. Embrace an iterative approach, refining methodologies for continuous enhancement and future analyses.

This step-by-step roadmap provides a structured framework for thorough and effective handling of a data analytics case study.

Now, after handling data analytics comes a crucial step; presenting the case study.

Presenting Your Data Analytics Case Study

Presenting a data analytics case study is a vital part of the process. When presenting your case study, clarity and organization are paramount.

To achieve this, follow these key steps:

Structuring Your Case Study: Start by outlining relevant and accurate main points. Ensure these points align with the problem addressed and the methodologies used in your analysis.

Crafting a Narrative with Data: Start with a brief overview of the issue, then explain your method and steps, covering data collection, cleaning, stats, and advanced modeling.

Visual Representation for Clarity: Utilize various visual aids—tables, graphs, and charts—to illustrate patterns, trends, and insights. Ensure these visuals are easy to comprehend and seamlessly support your narrative.

Highlighting Key Information: Use bullet points to emphasize essential information, maintaining clarity and allowing the audience to grasp key takeaways effortlessly. Bold key terms or phrases to draw attention and reinforce important points.

Addressing Audience Queries: Anticipate and be ready to answer audience questions regarding methods, assumptions, and results. Demonstrating a profound understanding of your analysis instills confidence in your work.

Integrity and Confidence in Delivery: Maintain a neutral tone and avoid exaggerated claims about findings. Present your case study with integrity, clarity, and confidence to ensure the audience appreciates and comprehends the significance of your work.

By organizing your presentation well, telling a clear story through your analysis, and using visuals wisely, you can effectively share your data analytics case study.

This method helps people understand better, stay engaged, and draw valuable conclusions from your work.

We hope by now, you are feeling very confident processing a case study. But with any process, there are challenges you may encounter.

Key Challenges in Data Analytics Case Studies

A data analytics case study can present various hurdles that necessitate strategic approaches for successful navigation:

Challenge 1: Data Quality and Consistency

Challenge: Inconsistent or poor-quality data can impede analysis, leading to erroneous insights and flawed conclusions.

Solution: Implement rigorous data validation processes, ensuring accuracy, completeness, and reliability. Employ data cleansing techniques to rectify inconsistencies and enhance overall data quality.

Challenge 2: Complexity and Scale of Data

Challenge: Managing vast volumes of data with diverse formats and complexities poses analytical challenges.

Solution: Utilize scalable data processing frameworks and tools capable of handling diverse data types. Implement efficient data storage and retrieval systems to manage large-scale datasets effectively.

Challenge 3: Interpretation and Contextual Understanding

Challenge: Interpreting data without contextual understanding or domain expertise can lead to misinterpretations.

Solution: Collaborate with domain experts to contextualize data and derive relevant insights. Invest in understanding the nuances of the industry or domain under analysis to ensure accurate interpretations.

Challenge 4: Privacy and Ethical Concerns

Challenge: Balancing data access for analysis while respecting privacy and ethical boundaries poses a challenge.

Solution: Implement robust data governance frameworks that prioritize data privacy and ethical considerations. Ensure compliance with regulatory standards and ethical guidelines throughout the analysis process.

Challenge 5: Resource Limitations and Time Constraints

Challenge: Limited resources and time constraints hinder comprehensive analysis and exhaustive data exploration.

Solution: Prioritize key objectives and allocate resources efficiently. Employ agile methodologies to iteratively analyze and derive insights, focusing on the most impactful aspects within the given timeframe.

Recognizing these challenges is key; it helps data analysts adopt proactive strategies to mitigate obstacles. This enhances the effectiveness and reliability of insights derived from a data analytics case study.

Now, let’s talk about the best software tools you should use when working with case studies.

Top 5 Software Tools for Case Studies

In the realm of case studies within data analytics, leveraging the right software tools is essential.

Here are some top-notch options:

Tableau : Renowned for its data visualization prowess, Tableau transforms raw data into interactive, visually compelling representations, ideal for presenting insights within a case study.

Python and R Libraries: These flexible programming languages provide many tools for handling data, doing statistics, and working with machine learning, meeting various needs in case studies.

Microsoft Excel : A staple tool for data analytics, Excel provides a user-friendly interface for basic analytics, making it useful for initial data exploration in a case study.

SQL Databases : Structured Query Language (SQL) databases assist in managing and querying large datasets, essential for organizing case study data effectively.

Statistical Software (e.g., SPSS , SAS ): Specialized statistical software enables in-depth statistical analysis, aiding in deriving precise insights from case study data.

Choosing the best mix of these tools, tailored to each case study’s needs, greatly boosts analytical abilities and results in data analytics.

Final Thoughts

Case studies in data analytics are helpful guides. They give real-world insights, improve skills, and show how data-driven decisions work.

Using case studies helps analysts learn, be creative, and make essential decisions confidently in their data work.

Check out our latest clip below to further your learning!

Frequently Asked Questions

What are the key steps to analyzing a data analytics case study.

When analyzing a case study, you should follow these steps:

Clarify the problem : Ensure you thoroughly understand the problem statement and the scope of the analysis.

Make assumptions : Define your assumptions to establish a feasible framework for analyzing the case.

Gather context : Acquire relevant information and context to support your analysis.

Analyze the data : Perform calculations, create visualizations, and conduct statistical analysis on the data.

Provide insights : Draw conclusions and develop actionable insights based on your analysis.

How can you effectively interpret results during a data scientist case study job interview?

During your next data science interview, interpret case study results succinctly and clearly. Utilize visual aids and numerical data to bolster your explanations, ensuring comprehension.

Frame the results in an audience-friendly manner, emphasizing relevance. Concentrate on deriving insights and actionable steps from the outcomes.

How do you showcase your data analyst skills in a project?

To demonstrate your skills effectively, consider these essential steps. Begin by selecting a problem that allows you to exhibit your capacity to handle real-world challenges through analysis.

Methodically document each phase, encompassing data cleaning, visualization, statistical analysis, and the interpretation of findings.

Utilize descriptive analysis techniques and effectively communicate your insights using clear visual aids and straightforward language. Ensure your project code is well-structured, with detailed comments and documentation, showcasing your proficiency in handling data in an organized manner.

Lastly, emphasize your expertise in SQL queries, programming languages, and various analytics tools throughout the project. These steps collectively highlight your competence and proficiency as a skilled data analyst, demonstrating your capabilities within the project.

Can you provide an example of a successful data analytics project using key metrics?

A prime illustration is utilizing analytics in healthcare to forecast hospital readmissions. Analysts leverage electronic health records, patient demographics, and clinical data to identify high-risk individuals.

Implementing preventive measures based on these key metrics helps curtail readmission rates, enhancing patient outcomes and cutting healthcare expenses.

This demonstrates how data analytics, driven by metrics, effectively tackles real-world challenges, yielding impactful solutions.

Why would a company invest in data analytics?

Companies invest in data analytics to gain valuable insights, enabling informed decision-making and strategic planning. This investment helps optimize operations, understand customer behavior, and stay competitive in their industry.

Ultimately, leveraging data analytics empowers companies to make smarter, data-driven choices, leading to enhanced efficiency, innovation, and growth.

Related Posts

4 Types of Data Analytics: Explained

Data Analytics

In a world full of data, data analytics is the heart and soul of an operation. It's what transforms raw...

Data Analytics Outsourcing: Pros and Cons Explained

In today's data-driven world, businesses are constantly swimming in a sea of information, seeking the...

What Does a Data Analyst Do on a Daily Basis?

In the digital age, data plays a significant role in helping organizations make informed decisions and...

• Open access
• Published: 22 April 2024

Artificial intelligence and medical education: application in classroom instruction and student assessment using a pharmacology & therapeutics case study

• Kannan Sridharan 1 &
• Reginald P. Sequeira 1  

BMC Medical Education volume  24 , Article number:  431 ( 2024 ) Cite this article

Metrics details

Artificial intelligence (AI) tools are designed to create or generate content from their trained parameters using an online conversational interface. AI has opened new avenues in redefining the role boundaries of teachers and learners and has the potential to impact the teaching-learning process.

In this descriptive proof-of- concept cross-sectional study we have explored the application of three generative AI tools on drug treatment of hypertension theme to generate: (1) specific learning outcomes (SLOs); (2) test items (MCQs- A type and case cluster; SAQs; OSPE); (3) test standard-setting parameters for medical students.

Analysis of AI-generated output showed profound homology but divergence in quality and responsiveness to refining search queries. The SLOs identified key domains of antihypertensive pharmacology and therapeutics relevant to stages of the medical program, stated with appropriate action verbs as per Bloom’s taxonomy. Test items often had clinical vignettes aligned with the key domain stated in search queries. Some test items related to A-type MCQs had construction defects, multiple correct answers, and dubious appropriateness to the learner’s stage. ChatGPT generated explanations for test items, this enhancing usefulness to support self-study by learners. Integrated case-cluster items had focused clinical case description vignettes, integration across disciplines, and targeted higher levels of competencies. The response of AI tools on standard-setting varied. Individual questions for each SAQ clinical scenario were mostly open-ended. The AI-generated OSPE test items were appropriate for the learner’s stage and identified relevant pharmacotherapeutic issues. The model answers supplied for both SAQs and OSPEs can aid course instructors in planning classroom lessons, identifying suitable instructional methods, establishing rubrics for grading, and for learners as a study guide. Key lessons learnt for improving AI-generated test item quality are outlined.

Conclusions

AI tools are useful adjuncts to plan instructional methods, identify themes for test blueprinting, generate test items, and guide test standard-setting appropriate to learners’ stage in the medical program. However, experts need to review the content validity of AI-generated output. We expect AIs to influence the medical education landscape to empower learners, and to align competencies with curriculum implementation. AI literacy is an essential competency for health professionals.

Peer Review reports

Artificial intelligence (AI) has great potential to revolutionize the field of medical education from curricular conception to assessment [ 1 ]. AIs used in medical education are mostly generative AI large language models that were developed and validated based on billions to trillions of parameters [ 2 ]. AIs hold promise in the incorporation of history-taking, assessment, diagnosis, and management of various disorders [ 3 ]. While applications of AIs in undergraduate medical training are being explored, huge ethical challenges remain in terms of data collection, maintaining anonymity, consent, and ownership of the provided data [ 4 ]. AIs hold a promising role amongst learners because they can deliver a personalized learning experience by tracking their progress and providing real-time feedback, thereby enhancing their understanding in the areas they are finding difficult [ 5 ]. Consequently, a recent survey has shown that medical students have expressed their interest in acquiring competencies related to the use of AIs in healthcare during their undergraduate medical training [ 6 ].

Pharmacology and Therapeutics (P & T) is a core discipline embedded in the undergraduate medical curriculum, mostly in the pre-clerkship phase. However, the application of therapeutic principles forms one of the key learning objectives during the clerkship phase of the undergraduate medical career. Student assessment in pharmacology & therapeutics (P&T) is with test items such as multiple-choice questions (MCQs), integrated case cluster questions, short answer questions (SAQs), and objective structured practical examination (OSPE) in the undergraduate medical curriculum. It has been argued that AIs possess the ability to communicate an idea more creatively than humans [ 7 ]. It is imperative that with access to billions of trillions of datasets the AI platforms hold promise in playing a crucial role in the conception of various test items related to any of the disciplines in the undergraduate medical curriculum. Additionally, AIs provide an optimized curriculum for a program/course/topic addressing multidimensional problems [ 8 ], although robust evidence for this claim is lacking.

The existing literature has evaluated the knowledge, attitude, and perceptions of adopting AI in medical education. Integration of AIs in medical education is the need of the hour in all health professional education. However, the academic medical fraternity facing challenges in the incorporation of AIs in the medical curriculum due to factors such as inadequate grounding in data analytics, lack of high-quality firm evidence favoring the utility of AIs in medical education, and lack of funding [ 9 ]. Open-access AI platforms are available free to users without any restrictions. Hence, as a proof-of-concept, we chose to explore the utility of three AI platforms to identify specific learning objectives (SLOs) related to pharmacology discipline in the management of hypertension for medical students at different stages of their medical training.

Study design and ethics

The present study is observational, cross-sectional in design, conducted in the Department of Pharmacology & Therapeutics, College of Medicine and Medical Sciences, Arabian Gulf University, Kingdom of Bahrain, between April and August 2023. Ethical Committee approval was not sought given the nature of this study that neither had any interaction with humans, nor collection of any personal data was involved.

Study procedure

We conducted the present study in May-June 2023 with the Poe© chatbot interface created by Quora© that provides access to the following three AI platforms:

Sage Poe [ 10 ]: A generative AI search engine developed by Anthropic © that conceives a response based on the written input provided. Quora has renamed Sage Poe as Assistant © from July 2023 onwards.

Claude-Instant [ 11 ]: A retrieval-based AI search engine developed by Anthropic © that collates a response based on pre-written responses amongst the existing databases.

ChatGPT version 3.5 [ 12 ]: A generative architecture-based AI search engine developed by OpenAI © trained on large and diverse datasets.

We queried the chatbots to generate SLOs, A-type MCQs, integrated case cluster MCQs, integrated SAQs, and OSPE test items in the domain of systemic hypertension related to the P&T discipline. Separate prompts were used to generate outputs for pre-clerkship (preclinical) phase students, and at the time of graduation (before starting residency programs). Additionally, we have also evaluated the ability of these AI platforms to estimate the proportion of students correctly answering these test items. We used the following queries for each of these objectives:

Specific learning objectives

Can you generate specific learning objectives in the pharmacology discipline relevant to undergraduate medical students during their pre-clerkship phase related to anti-hypertensive drugs?

Can you generate specific learning objectives in the pharmacology discipline relevant to undergraduate medical students at the time of graduation related to anti-hypertensive drugs?

A-type MCQs

In the initial query used for A-type of item, we specified the domains (such as the mechanism of action, pharmacokinetics, adverse reactions, and indications) so that a sample of test items generated without any theme-related clutter, shown below:

Write 20 single best answer MCQs with 5 choices related to anti-hypertensive drugs for undergraduate medical students during the pre-clerkship phase of which 5 MCQs should be related to mechanism of action, 5 MCQs related to pharmacokinetics, 5 MCQs related to adverse reactions, and 5 MCQs should be related to indications.

The MCQs generated with the above search query were not based on clinical vignettes. We queried again to generate MCQs using clinical vignettes specifically because most medical schools have adopted problem-based learning (PBL) in their medical curriculum.

Write 20 single best answer MCQs with 5 choices related to anti-hypertensive drugs for undergraduate medical students during the pre-clerkship phase using a clinical vignette for each MCQ of which 5 MCQs should be related to the mechanism of action, 5 MCQs related to pharmacokinetics, 5 MCQs related to adverse reactions, and 5 MCQs should be related to indications.

We attempted to explore whether AI platforms can provide useful guidance on standard-setting. Hence, we used the following search query.

Can you do a simulation with 100 undergraduate medical students to take the above questions and let me know what percentage of students got each MCQ correct?

Integrated case cluster MCQs

Write 20 integrated case cluster MCQs with 2 questions in each cluster with 5 choices for undergraduate medical students during the pre-clerkship phase integrating pharmacology and physiology related to systemic hypertension with a case vignette.

Write 20 integrated case cluster MCQs with 2 questions in each cluster with 5 choices for undergraduate medical students during the pre-clerkship phase integrating pharmacology and physiology related to systemic hypertension with a case vignette. Please do not include ‘none of the above’ as the choice. (This modified search query was used because test items with ‘None of the above’ option were generated with the previous search query).

Write 20 integrated case cluster MCQs with 2 questions in each cluster with 5 choices for undergraduate medical students at the time of graduation integrating pharmacology and physiology related to systemic hypertension with a case vignette.

Integrated short answer questions

Write a short answer question scenario with difficult questions based on the theme of a newly diagnosed hypertensive patient for undergraduate medical students with the main objectives related to the physiology of blood pressure regulation, risk factors for systemic hypertension, pathophysiology of systemic hypertension, pathological changes in the systemic blood vessels in hypertension, pharmacological management, and non-pharmacological treatment of systemic hypertension.

Write a short answer question scenario with moderately difficult questions based on the theme of a newly diagnosed hypertensive patient for undergraduate medical students with the main objectives related to the physiology of blood pressure regulation, risk factors for systemic hypertension, pathophysiology of systemic hypertension, pathological changes in the systemic blood vessels in hypertension, pharmacological management, and non-pharmacological treatment of systemic hypertension.

Write a short answer question scenario with questions based on the theme of a newly diagnosed hypertensive patient for undergraduate medical students at the time of graduation with the main objectives related to the physiology of blood pressure regulation, risk factors for systemic hypertension, pathophysiology of systemic hypertension, pathological changes in the systemic blood vessels in hypertension, pharmacological management, and non-pharmacological treatment of systemic hypertension.

Can you generate 5 OSPE pharmacology and therapeutics prescription writing exercises for the assessment of undergraduate medical students at the time of graduation related to anti-hypertensive drugs?

Can you generate 5 OSPE pharmacology and therapeutics prescription writing exercises containing appropriate instructions for the patients for the assessment of undergraduate medical students during their pre-clerkship phase related to anti-hypertensive drugs?

Can you generate 5 OSPE pharmacology and therapeutics prescription writing exercises containing appropriate instructions for the patients for the assessment of undergraduate medical students at the time of graduation related to anti-hypertensive drugs?

Both authors independently evaluated the AI-generated outputs, and a consensus was reached. We cross-checked the veracity of answers suggested by AIs as per the Joint National Commission Guidelines (JNC-8) and Goodman and Gilman’s The Pharmacological Basis of Therapeutics (2023), a reference textbook [ 13 , 14 ]. Errors in the A-type MCQs were categorized as item construction defects, multiple correct answers, and uncertain appropriateness to the learner’s level. Test items in the integrated case cluster MCQs, SAQs and OSPEs were evaluated with the Preliminary Conceptual Framework for Establishing Content Validity of AI-Generated Test Items based on the following domains: technical accuracy, comprehensiveness, education level, and lack of construction defects (Table  1 ). The responses were categorized as complete and deficient for each domain.

The pre-clerkship phase SLOs identified by Sage Poe, Claude-Instant, and ChatGPT are listed in the electronic supplementary materials 1 – 3 , respectively. In general, a broad homology in SLOs generated by the three AI platforms was observed. All AI platforms identified appropriate action verbs as per Bloom’s taxonomy to state the SLO; action verbs such as describe, explain, recognize, discuss, identify, recommend, and interpret are used to state the learning outcome. The specific, measurable, achievable, relevant, time-bound (SMART) SLOs generated by each AI platform slightly varied. All key domains of antihypertensive pharmacology to be achieved during the pre-clerkship (pre-clinical) years were relevant for graduating doctors. The SLOs addressed current JNC Treatment Guidelines recommended classes of antihypertensive drugs, the mechanism of action, pharmacokinetics, adverse effects, indications/contraindications, dosage adjustments, monitoring therapy, and principles of monotherapy and combination therapy.

The SLOs to be achieved by undergraduate medical students at the time of graduation identified by Sage Poe, Claude-Instant, and ChatGPT listed in electronic supplementary materials 4 – 6 , respectively. The identified SLOs emphasize the application of pharmacology knowledge within a clinical context, focusing on competencies needed to function independently in early residency stages. These SLOs go beyond knowledge recall and mechanisms of action to encompass competencies related to clinical problem-solving, rational prescribing, and holistic patient management. The SLOs generated require higher cognitive ability of the learner: action verbs such as demonstrate, apply, evaluate, analyze, develop, justify, recommend, interpret, manage, adjust, educate, refer, design, initiate & titrate were frequently used.

The MCQs for the pre-clerkship phase identified by Sage Poe, Claude-Instant, and ChatGPT listed in the electronic supplementary materials 7 – 9 , respectively, and those identified with the search query based on the clinical vignette in electronic supplementary materials ( 10 – 12 ).

All MCQs generated by the AIs in each of the four domains specified [mechanism of action (MOA); pharmacokinetics; adverse drug reactions (ADRs), and indications for antihypertensive drugs] are quality test items with potential content validity. The test items on MOA generated by Sage Poe included themes such as renin-angiotensin-aldosterone (RAAS) system, beta-adrenergic blockers (BB), calcium channel blockers (CCB), potassium channel openers, and centrally acting antihypertensives; on pharmacokinetics included high oral bioavailability/metabolism in liver [angiotensin receptor blocker (ARB)-losartan], long half-life and renal elimination [angiotensin converting enzyme inhibitors (ACEI)-lisinopril], metabolism by both liver and kidney (beta-blocker (BB)-metoprolol], rapid onset- short duration of action (direct vasodilator-hydralazine), and long-acting transdermal drug delivery (centrally acting-clonidine). Regarding the ADR theme, dry cough, angioedema, and hyperkalemia by ACEIs in susceptible patients, reflex tachycardia by CCB/amlodipine, and orthostatic hypotension by CCB/verapamil addressed. Clinical indications included the drug of choice for hypertensive patients with concomitant comorbidity such as diabetics (ACEI-lisinopril), heart failure and low ejection fraction (BB-carvedilol), hypertensive urgency/emergency (alpha cum beta receptor blocker-labetalol), stroke in patients with history recurrent stroke or transient ischemic attack (ARB-losartan), and preeclampsia (methyldopa).

Almost similar themes under each domain were identified by the Claude-Instant AI platform with few notable exceptions: hydrochlorothiazide (instead of clonidine) in MOA and pharmacokinetics domains, respectively; under the ADR domain ankle edema/ amlodipine, sexual dysfunction and fatigue in male due to alpha-1 receptor blocker; under clinical indications the best initial monotherapy for clinical scenarios such as a 55-year old male with Stage-2 hypertension; a 75-year-old man Stage 1 hypertension; a 35-year-old man with Stage I hypertension working on night shifts; and a 40-year-old man with stage 1 hypertension and hyperlipidemia.

As with Claude-Instant AI, ChatGPT-generated test items on MOA were mostly similar. However, under the pharmacokinetic domain, immediate- and extended-release metoprolol, the effect of food to enhance the oral bioavailability of ramipril, and the highest oral bioavailability of amlodipine compared to other commonly used antihypertensives were the themes identified. Whereas the other ADR themes remained similar, constipation due to verapamil was a new theme addressed. Notably, in this test item, amlodipine was an option that increased the difficulty of this test item because amlodipine therapy is also associated with constipation, albeit to a lesser extent, compared to verapamil. In the clinical indication domain, the case description asking “most commonly used in the treatment of hypertension and heart failure” is controversial because the options listed included losartan, ramipril, and hydrochlorothiazide but the suggested correct answer was ramipril. This is a good example to stress the importance of vetting the AI-generated MCQ by experts for content validity and to assure robust psychometrics. The MCQ on the most used drug in the treatment of “hypertension and diabetic nephropathy” is more explicit as opposed to “hypertension and diabetes” by Claude-Instant because the therapeutic concept of reducing or delaying nephropathy must be distinguished from prevention of nephropathy, although either an ACEI or ARB is the drug of choice for both indications.

It is important to align student assessment to the curriculum; in the PBL curriculum, MCQs with a clinical vignette are preferred. The modification of the query specifying the search to generate MCQs with a clinical vignette on domains specified previously gave appropriate output by all three AI platforms evaluated (Sage Poe; Claude- Instant; Chat GPT). The scenarios generated had a good clinical fidelity and educational fit for the pre-clerkship student perspective.

The errors observed with AI outputs on the A-type MCQs are summarized in Table  2 . No significant pattern was observed except that Claude-Instant© generated test items in a stereotyped format such as the same choices for all test items related to pharmacokinetics and indications, and all the test items in the ADR domain are linked to the mechanisms of action of drugs. This illustrates the importance of reviewing AI-generated test items by content experts for content validity to ensure alignment with evidence-based medicine and up-to-date treatment guidelines.

The test items generated by ChatGPT had the advantage of explanations supplied rendering these more useful for learners to support self-study. The following examples illustrate this assertion: “ A patient with hypertension is started on a medication that works by blocking beta-1 receptors in the heart (metoprolol)”. Metoprolol is a beta blocker that works by blocking beta-1 receptors in the heart, which reduces heart rate and cardiac output, resulting in a decrease in blood pressure. However, this explanation is incomplete because there is no mention of other less important mechanisms, of beta receptor blockers on renin release. Also, these MCQs were mostly recall type: Which of the following medications is known to have a significant first-pass effect? The explanation reads: propranolol is known to have a significant first pass-effect, meaning that a large portion of the drug is metabolized by the liver before it reaches systemic circulation. Losartan, amlodipine, ramipril, and hydrochlorothiazide do not have significant first-pass effect. However, it is also important to extend the explanation further by stating that the first-pass effect of propranolol does not lead to total loss of pharmacological activity because the metabolite hydroxy propranolol also has potent beta-blocking activity. Another MCQ test item had a construction defect: “A patient with hypertension is started on a medication that can cause photosensitivity. Which of the following medications is most likely responsible?” Options included: losartan, amlodipine, ramipril, hydrochlorothiazide, hydrochlorothiazide/triamterene. The explanation states that hydrochlorothiazide (HCTZ) can cause photosensitivity, which is increased sensitivity to sunlight that can cause skin rashes and sunburns. Losartan, amlodipine, ramipril, and HCTZ/triamterene are less likely to cause photosensitivity. However, it is irrational to claim that HCTZ/triamterene, one of the wrong options, is less likely to cause photosensitivity. The difficulty index of such test items is likely unacceptable in high-stake tests to make equitable psychometric decisions.

The responses from Sage Poe, Claude-Instant, and ChatGPT on guidance for standard-setting methods are listed in the electronic supplementary materials 13 – 15 . Sage Poe offered this information with the caveat that “the results of this simulation were purely hypothetical and do not reflect the actual performance of any real students”. The simulation estimates of examinees correctly answering test items ranged from 60 to 90% for the mechanism of action, 65–85% for pharmacokinetics, 60–80% for adverse reactions, and 75–90% for clinical indications of antihypertensives.

In contrast, Claude-Instant admitted that “Performing a full simulation with 100 medical students is beyond the scope of what I can do as an AI assistant. I can generate sample MCQ questions and answers, but I do not have access to a population of medical students to administer the questions. A true simulation that administers questions to real students and analyzes the results would require access to a database of medical students, a platform to deliver the questions, and code to analyze the responses. As an AI assistant, I lack these capabilities. While I cannot perform a full simulation, here are some considerations for administering MCQ questions to medical students: provide details on the purpose and instructions for the test to ensure students understand what is expected out of them; consider including some easier questions in addition to more challenging ones to boost students’ confidence and motivation; avoid ambiguous wording and ensure each question has only one unambiguously correct answer option; when analyzing results, look for questions factors that may have impacted performance, like unclear wording or answer options that are too similar. Focusing on weak questions can help improve future tests; compare performance across different student groups to identify areas where more teaching may be needed; provide detailed answer explanations and review sessions after the test to help students learn from any errors and reinforce correct concepts”. However, ChatGPT offered the simulation result estimates for the 20 MCQ on antihypertensive drugs: mechanism of action ranged from 67 to 92%, pharmacokinetics 63–86%, adverse effects 65–82%, and clinical indications 64–89%. Furthermore, it also stated that “Overall, the performance of the students was quite good, with most questions having a response rate of over 70%. However, there were some questions where the projected correct response rate was rather low, such as Question #5 (Mechanism of Action of Hydrochlorothiazide; see Electronic Supplementary Material 12 ) and Question 18 (Indications for Verapamil; see Electronic Supplementary Material 10 ). This may suggest areas where students need more focused education or review.”

We asked AI assistants to generate 20 integrated case cluster MCQs with 2 test items in each cluster with five options for undergraduate medical students in the pre-clerkship phase integrating pharmacology and physiology related to systemic hypertension with a case vignette and the responses by Sage Poe, Claude-Instant, and ChatGPT are listed in the electronic supplementary materials ( 16 – 18 ). In all instances, the test items generated had focused case descriptions in the form of a clinical vignette, and horizontal integration across the pathophysiology of hypertension and pharmacology of antihypertensive drugs. These test items mostly targeted the ‘knows (knowledge)’ or ‘knows how (competence)’ level on Miller’s pyramid and are suitable for assessing the clinical competence of pre-clerkship medical students, especially in an integrated PBL curriculum. Both the AI assistants generated excellent clinical vignettes and themes; however, most of the cluster MCQs by ChatGPT had “None of the above” as an option, which is often considered a test item construction flaw. Notwithstanding these limitations, case cluster integrated test items are valuable for learners to integrate their knowledge of different basic medical sciences and their application to clinical sciences. This integrated approach can be used for both instructional and student assessment purposes to make the course more meaningful. Indeed, one of the basic tenets of PBL is curriculum integration.

In the next query, we asked AI assistants to write integrated case cluster MCQs with 2 test items in each cluster with 5 options for undergraduate medical students at the time of graduation integrating pharmacology and physiology of hypertension with a case vignette. The responses are listed in the electronic supplementary materials 19 – 21 . Claude-Instant has provided only partial responses to both the queries. Overall, the information provided in case vignettes requires the learner to interpret the clinical information and make therapeutic decisions. Such test items are appropriate for assessing the minimum competency of medical school graduates to start internship or residency programs; these MCQs are generally comparable to test items used in USMLE Part 2. The evaluation of the integrated case cluster test items provided by all the AI platforms is summarized in Table  3 . In general, the AI outputs had at least one construction defect, and did not include all the core sub-topics to a sufficient degree.

When asked to simulate the above-generated test items to 100 undergraduate medical students at the time of graduation and provide a percentage of students who are likely to correctly answer each item, the AI assistant responded:

“ As an AI language model, I cannot simulate the responses of 100 undergraduate medical students likely to obtain the correct answer for each question. However, I can provide some general information about the difficulty level of each question based on the complexity of the concepts being tested and the level of integration between pharmacology and physiology ”.

AI assistant went on to clarify that questions that require knowledge of basic pharmacology principles, such as the mechanism of action of specific drugs, are likely to be easier for students to answer correctly. Test items that require an understanding of the physiological mechanisms underlying hypertension and correlating with symptoms are likely to be more challenging for students. The AI assistant sorted these test items into two categories accordingly. Overall, the difficulty level of the test item is based on the level of integration between pharmacology and pathophysiology. Test items that require an understanding of both pharmacological and physiological mechanisms are likely to be more challenging for students requiring a strong foundation in both pharmacology and physiology concepts to be able to correctly answer integrated case-cluster MCQs.

Short answer questions

The responses to a search query on generating SAQs appropriate to the pre-clerkship phase Sage Poe, Claude-Instant, and ChatGPT generated items are listed in the electronic supplementary materials 22 – 24 for difficult questions and 25–27 for moderately difficult questions.

It is apparent from these case vignette descriptions that the short answer question format varied. Accordingly, the scope for asking individual questions for each scenario is open-ended. In all instances, model answers are supplied which are helpful for the course instructor to plan classroom lessons, identify appropriate instructional methods, and establish rubrics for grading the answer scripts, and as a study guide for students.

We then wanted to see to what extent AI can differentiate the difficulty of the SAQ by replacing the search term “difficult” with “moderately difficult” in the above search prompt: the changes in the revised case scenarios are substantial. Perhaps the context of learning and practice (and the level of the student in the MD/medical program) may determine the difficulty level of SAQ generated. It is worth noting that on changing the search from cardiology to internal medicine rotation in Sage Poe the case description also changed. Thus, it is essential to select an appropriate AI assistant, perhaps by trial and error, to generate quality SAQs. Most of the individual questions tested stand-alone knowledge and did not require students to demonstrate integration.

The responses of Sage Poe, Claude-Instant, and ChatGPT for the search query to generate SAQs at the time of graduation are listed in the electronic supplementary materials 28 – 30 . It is interesting to note how AI assistants considered the stage of the learner while generating the SAQ. The response by Sage Poe is illustrative for comparison. “You are a newly graduated medical student who is working in a hospital” versus “You are a medical student in your pre-clerkship.”

Some questions were retained, deleted, or modified to align with competency appropriate to the context (Electronic Supplementary Materials 28 – 30 ). Overall, the test items at both levels from all AI platforms were technically accurate and thorough addressing the topics related to different disciplines (Table  3 ). The differences in learning objective transition are summarized in Table  4 . A comparison of learning objectives revealed that almost all objectives remained the same except for a few (Table  5 ).

A similar trend was apparent with test items generated by other AI assistants, such as ChatGPT. The contrasting differences in questions are illustrated by the vertical integration of basic sciences and clinical sciences (Table  6 ).

Taken together, these in-depth qualitative comparisons suggest that AI assistants such as Sage Poe and ChatGPT consider the learner’s stage of training in designing test items, learning outcomes, and answers expected from the examinee. It is critical to state the search query explicitly to generate quality output by AI assistants.

The OSPE test items generated by Claude-Instant and ChatGPT appropriate to the pre-clerkship phase (without mentioning “appropriate instructions for the patients”) are listed in the electronic supplementary materials 31 and 32 and with patient instructions on the electronic supplementary materials 33 and 34 . For reasons unknown, Sage Poe did not provide any response to this search query.

The five OSPE items generated were suitable to assess the prescription writing competency of pre-clerkship medical students. The clinical scenarios identified by the three AI platforms were comparable; these scenarios include patients with hypertension and impaired glucose tolerance in a 65-year-old male, hypertension with chronic kidney disease (CKD) in a 55-year-old woman, resistant hypertension with obstructive sleep apnea in a 45-year-old man, and gestational hypertension at 32 weeks in a 35-year-old (Claude-Instant AI). Incorporating appropriate instructions facilitates the learner’s ability to educate patients and maximize safe and effective therapy. The OSPE item required students to write a prescription with guidance to start conservatively, choose an appropriate antihypertensive drug class (drug) based on the patients’ profile, specifying drug name, dose, dosing frequency, drug quantity to be dispensed, patient name, date, refill, and caution as appropriate, in addition to prescribers’ name, signature, and license number. In contrast, ChatGPT identified clinical scenarios to include patients with hypertension and CKD, hypertension and bronchial asthma, gestational diabetes, hypertension and heart failure, and hypertension and gout (ChatGPT). Guidance for dosage titration, warnings to be aware, safety monitoring, and frequency of follow-up and dose adjustment. These test items are designed to assess learners’ knowledge of P & T of antihypertensives, as well as their ability to provide appropriate instructions to patients. These clinical scenarios for writing prescriptions assess students’ ability to choose an appropriate drug class, write prescriptions with proper labeling and dosing, reflect drug safety profiles, and risk factors, and make modifications to meet the requirements of special populations. The prescription is required to state the drug name, dose, dosing frequency, patient name, date, refills, and cautions or instructions as needed. A conservative starting dose, once or twice daily dosing frequency based on the drug, and instructions to titrate the dose slowly if required.

The responses from Claude-Instant and ChatGPT for the search query related to generating OSPE test items at the time of graduation are listed in electronic supplementary materials 35 and 36 . In contrast to the pre-clerkship phase, OSPEs generated for graduating doctors’ competence assessed more advanced drug therapy comprehension. For example, writing a prescription for:

(1) A 65-year- old male with resistant hypertension and CKD stage 3 to optimize antihypertensive regimen required the answer to include starting ACEI and diuretic, titrating the dosage over two weeks, considering adding spironolactone or substituting ACEI with an ARB, and need to closely monitor serum electrolytes and kidney function closely.

(2) A 55-year-old woman with hypertension and paroxysmal arrhythmia required the answer to include switching ACEI to ARB due to cough, adding a CCB or beta blocker for rate control needs, and adjusting the dosage slowly and monitoring for side effects.

(3) A 45-year-old man with masked hypertension and obstructive sleep apnea require adding a centrally acting antihypertensive at bedtime and increasing dosage as needed based on home blood pressure monitoring and refer to CPAP if not already using one.

(4) A 75-year-old woman with isolated systolic hypertension and autonomic dysfunction to require stopping diuretic and switching to an alpha blocker, upward dosage adjustment and combining with other antihypertensives as needed based on postural blood pressure changes and symptoms.

(5) A 35-year-old pregnant woman with preeclampsia at 29 weeks require doubling methyldopa dose and consider adding labetalol or nifedipine based on severity and educate on signs of worsening and to follow-up immediately for any concerning symptoms.

These case scenarios are designed to assess the ability of the learner to comprehend the complexity of antihypertensive regimens, make evidence-based regimen adjustments, prescribe multidrug combinations based on therapeutic response and tolerability, monitor complex patients for complications, and educate patients about warning signs and follow-up.

A similar output was provided by ChatGPT, with clinical scenarios such as prescribing for patients with hypertension and myocardial infarction; hypertension and chronic obstructive pulmonary airway disease (COPD); hypertension and a history of angina; hypertension and a history of stroke, and hypertension and advanced renal failure. In these cases, wherever appropriate, pharmacotherapeutic issues like taking ramipril after food to reduce side effects such as giddiness; selection of the most appropriate beta-blocker such as nebivolol in patients with COPD comorbidity; the importance of taking amlodipine at the same time every day with or without food; preference for telmisartan among other ARBs in stroke; choosing furosemide in patients with hypertension and edema and taking the medication with food to reduce the risk of gastrointestinal adverse effect are stressed.

The AI outputs on OSPE test times were observed to be technically accurate, thorough in addressing core sub-topics suitable for the learner’s level and did not have any construction defects (Table  3 ). Both AIs provided the model answers with explanatory notes. This facilitates the use of such OSPEs for self-assessment by learners for formative assessment purposes. The detailed instructions are helpful in creating optimized therapy regimens, and designing evidence-based regimens, to provide appropriate instructions to patients with complex medical histories. One can rely on multiple AI sources to identify, shortlist required case scenarios, and OSPE items, and seek guidance on expected model answers with explanations. The model answer guidance for antihypertensive drug classes is more appropriate (rather than a specific drug of a given class) from a teaching/learning perspective. We believe that these scenarios can be refined further by providing a focused case history along with relevant clinical and laboratory data to enhance clinical fidelity and bring a closer fit to the competency framework.

In the present study, AI tools have generated SLOs that comply with the current principles of medical education [ 15 ]. AI tools are valuable in constructing SLOs and so are especially useful for medical fraternities where training in medical education is perceived as inadequate, more so in the early stages of their academic career. Data suggests that only a third of academics in medical schools have formal training in medical education [ 16 ] which is a limitation. Thus, the credibility of alternatives, such as the AIs, is evaluated to generate appropriate course learning outcomes.

We observed that the AI platforms in the present study generated quality test items suitable for different types of assessment purposes. The AI-generated outputs were similar with minor variation. We have used generative AIs in the present study that could generate new content from their training dataset [ 17 ]. Problem-based and interactive learning approaches are referred to as “bottom-up” where learners obtain first-hand experience in solving the cases first and then indulge in discussion with the educators to refine their understanding and critical thinking skills [ 18 ]. We suggest that AI tools can be useful for this approach for imparting the core knowledge and skills related to Pharmacology and Therapeutics to undergraduate medical students. A recent scoping review evaluating the barriers to writing quality test items based on 13 studies has concluded that motivation, time constraints, and scheduling were the most common [ 19 ]. AI tools can be valuable considering the quick generation of quality test items and time management. However, as observed in the present study, the AI-generated test items nevertheless require scrutiny by faculty members for content validity. Moreover, it is important to train faculty in AI technology-assisted teaching and learning. The General Medical Council recommends taking every opportunity to raise the profile of teaching in medical schools [ 20 ]. Hence, both the academic faculty and the institution must consider investing resources in AI training to ensure appropriate use of the technology [ 21 ].

The AI outputs assessed in the present study had errors, particularly with A-type MCQs. One notable observation was that often the AI tools were unable to differentiate the differences between ACEIs and ARBs. AI platforms access several structured and unstructured data, in addition to images, audio, and videos. Hence, the AI platforms can commit errors due to extracting details from unauthenticated sources [ 22 ] created a framework identifying 28 factors for reconstructing the path of AI failures and for determining corrective actions. This is an area of interest for AI technical experts to explore. Also, this further iterates the need for human examination of test items before using them for assessment purposes.

There are concerns that AIs can memorize and provide answers from their training dataset, which they are not supposed to do [ 23 ]. Hence, the use of AIs-generated test items for summative examinations is debatable. It is essential to ensure and enhance the security features of AI tools to reduce or eliminate cross-contamination of test items. Researchers have emphasized that AI tools will only reach their potential if developers and users can access full-text non-PDF formats that help machines comprehend research papers and generate the output [ 24 ].

AI platforms may not always have access to all standard treatment guidelines. However, in the present study, it was observed that all three AI platforms generally provided appropriate test items regarding the choice of medications, aligning with recommendations from contemporary guidelines and standard textbooks in pharmacology and therapeutics. The prompts used in the study were specifically focused on the pre-clerkship phase of the undergraduate medical curriculum (and at the time of their graduation) and assessed fundamental core concepts, which were also reflected in the AI outputs. Additionally, the recommended first-line antihypertensive drug classes have been established for several decades, and information regarding their pharmacokinetics, ADRs, and indications is well-documented in the literature.

Different paradigms and learning theories have been proposed to support AI in education. These paradigms include AI- directed (learner as recipient), AI-supported (learner as collaborator), and AI-empowered (learner as leader) that are based on Behaviorism, Cognitive-Social constructivism, and Connectivism-Complex adaptive systems, respectively [ 25 ]. AI techniques have potential to stimulate and advance instructional and learning sciences. More recently a three- level model that synthesizes and unifies existing learning theories to model the roles of AIs in promoting learning process has been proposed [ 26 ]. The different components of our study rely upon these paradigms and learning theories as the theoretical underpinning.

Strengths and limitations

To the best of our knowledge, this is the first study evaluating the utility of AI platforms in generating test items related to a discipline in the undergraduate medical curriculum. We have evaluated the AI’s ability to generate outputs related to most types of assessment in the undergraduate medical curriculum. The key lessons learnt for improving the AI-generated test item quality from the present study are outlined in Table  7 . We used a structured framework for assessing the content validity of the test items. However, we have demonstrated using a single case study (hypertension) as a pilot experiment. We chose to evaluate anti-hypertensive drugs as it is a core learning objective and one of the most common disorders relevant to undergraduate medical curricula worldwide. It would be interesting to explore the output from AI platforms for other common (and uncommon/region-specific) disorders, non-/semi-core objectives, and disciplines other than Pharmacology and Therapeutics. An area of interest would be to look at the content validity of the test items generated for different curricula (such as problem-based, integrated, case-based, and competency-based) during different stages of the learning process. Also, we did not attempt to evaluate the generation of flowcharts, algorithms, or figures for generating test items. Another potential area for exploring the utility of AIs in medical education would be repeated procedural practices such as the administration of drugs through different routes by trainee residents [ 27 ]. Several AI tools have been identified for potential application in enhancing classroom instructions and assessment purposes pending validation in prospective studies [ 28 ]. Lastly, we did not administer the AI-generated test items to students and assessed their performance and so could not comment on the validity of test item discrimination and difficulty indices. Additionally, there is a need to confirm the generalizability of the findings to other complex areas in the same discipline as well as in other disciplines that pave way for future studies. The conceptual framework used in the present study for evaluating the AI-generated test items needs to be validated in a larger population. Future studies may also try to evaluate the variations in the AI outputs with repetition of the same queries.

Notwithstanding ongoing discussions and controversies, AI tools are potentially useful adjuncts to optimize instructional methods, test blueprinting, test item generation, and guidance for test standard-setting appropriate to learners’ stage in the medical program. However, experts need to critically review the content validity of AI-generated output. These challenges and caveats are to be addressed before the use of widespread use of AIs in medical education can be advocated.

Data availability

All the data included in this study are provided as Electronic Supplementary Materials.

Tolsgaard MG, Pusic MV, Sebok-Syer SS, Gin B, Svendsen MB, Syer MD, Brydges R, Cuddy MM, Boscardin CK. The fundamentals of Artificial Intelligence in medical education research: AMEE Guide 156. Med Teach. 2023;45(6):565–73.

Article   Google Scholar  

Sriwastwa A, Ravi P, Emmert A, Chokshi S, Kondor S, Dhal K, Patel P, Chepelev LL, Rybicki FJ, Gupta R. Generative AI for medical 3D printing: a comparison of ChatGPT outputs to reference standard education. 3D Print Med. 2023;9(1):21.

Azer SA, Guerrero APS. The challenges imposed by artificial intelligence: are we ready in medical education? BMC Med Educ. 2023;23(1):680.

Masters K. Ethical use of Artificial Intelligence in Health Professions Education: AMEE Guide 158. Med Teach. 2023;45(6):574–84.

Nagi F, Salih R, Alzubaidi M, Shah H, Alam T, Shah Z, Househ M. Applications of Artificial Intelligence (AI) in Medical Education: a scoping review. Stud Health Technol Inf. 2023;305:648–51.

Google Scholar  

Mehta N, Harish V, Bilimoria K, et al. Knowledge and attitudes on artificial intelligence in healthcare: a provincial survey study of medical students. MedEdPublish. 2021;10(1):75.

Mir MM, Mir GM, Raina NT, Mir SM, Mir SM, Miskeen E, Alharthi MH, Alamri MMS. Application of Artificial Intelligence in Medical Education: current scenario and future perspectives. J Adv Med Educ Prof. 2023;11(3):133–40.

Garg T. Artificial Intelligence in Medical Education. Am J Med. 2020;133(2):e68.

Matheny ME, Whicher D, Thadaney IS. Artificial intelligence in health care: a report from the National Academy of Medicine. JAMA. 2020;323(6):509–10.

Sage Poe. Available at: https://poe.com/Assistant (Accessed on. 3rd June 2023).

Claude-Instant: Available at: https://poe.com/Claude-instant (Accessed on 3rd. June 2023).

ChatGPT: Available at: https://poe.com/ChatGPT (Accessed on 3rd. June 2023).

James PA, Oparil S, Carter BL, Cushman WC, Dennison-Himmelfarb C, Handler J, Lackland DT, LeFevre ML, MacKenzie TD, Ogedegbe O, Smith SC Jr, Svetkey LP, Taler SJ, Townsend RR, Wright JT Jr, Narva AS, Ortiz E. 2014 evidence-based guideline for the management of high blood pressure in adults: report from the panel members appointed to the Eighth Joint National Committee (JNC 8). JAMA. 2014;311(5):507–20.

Eschenhagen T. Treatment of hypertension. In: Brunton LL, Knollmann BC, editors. Goodman & Gilman’s the pharmacological basis of therapeutics. 14th ed. New York: McGraw Hill; 2023.

Shabatura J. September. Using Bloom’s taxonomy to write effective learning outcomes. https://tips.uark.edu/using-blooms-taxonomy/ (Accessed on 19th 2023).

Trainor A, Richards JB. Training medical educators to teach: bridging the gap between perception and reality. Isr J Health Policy Res. 2021;10(1):75.

Boscardin C, Gin B, Golde PB, Hauer KE. ChatGPT and generative artificial intelligence for medical education: potential and opportunity. Acad Med. 2023. https://doi.org/10.1097/ACM.0000000000005439 . (Published ahead of print).

Duong MT, Rauschecker AM, Rudie JD, Chen PH, Cook TS, Bryan RN, Mohan S. Artificial intelligence for precision education in radiology. Br J Radiol. 2019;92(1103):20190389.

Karthikeyan S, O’Connor E, Hu W. Barriers and facilitators to writing quality items for medical school assessments - a scoping review. BMC Med Educ. 2019;19(1):123.

Developing teachers and trainers in undergraduate medical education. Advice supplementary to Tomorrow’s Doctors. (2009). https://www.gmc-uk.org/-/media/documents/Developing_teachers_and_trainers_in_undergraduate_medical_education___guidance_0815.pdf_56440721.pdf (Accessed on 19th September 2023).

Cooper A, Rodman A. AI and Medical Education - A 21st-Century Pandora’s Box. N Engl J Med. 2023;389(5):385–7.

Chanda SS, Banerjee DN. Omission and commission errors underlying AI failures. AI Soc. 2022;17:1–24.

Narayanan A, Kapoor S. ‘GPT-4 and Professional Benchmarks: The Wrong Answer to the Wrong Question’. Substack newsletter. AI Snake Oil (blog). https://aisnakeoil.substack.com/p/gpt-4-and-professional-benchmarks (Accessed on 19th September 2023).

Brainard J. November. As scientists face a flood of papers, AI developers aim to help. Science, 21 2023. doi.10.1126/science.adn0669.

Ouyang F, Jiao P. Artificial intelligence in education: the three paradigms. Computers Education: Artif Intell. 2021;2:100020.

Gibson D, Kovanovic V, Ifenthaler D, Dexter S, Feng S. Learning theories for artificial intelligence promoting learning processes. Br J Edu Technol. 2023;54(5):1125–46.

Guerrero DT, Asaad M, Rajesh A, Hassan A, Butler CE. Advancing Surgical Education: the Use of Artificial Intelligence in Surgical Training. Am Surg. 2023;89(1):49–54.

Lee S. AI tools for educators. EIT InnoEnergy Master School Teachers Conference. 2023. https://www.slideshare.net/ignatia/ai-toolkit-for-educators?from_action=save (Accessed on 24th September 2023).

Download references

Author information

Authors and affiliations.

Department of Pharmacology & Therapeutics, College of Medicine & Medical Sciences, Arabian Gulf University, Manama, Kingdom of Bahrain

Kannan Sridharan & Reginald P. Sequeira

You can also search for this author in PubMed   Google Scholar

Contributions

RPS– Conceived the idea; KS– Data collection and curation; RPS and KS– Data analysis; RPS and KS– wrote the first draft and were involved in all the revisions.

Corresponding author

Correspondence to Kannan Sridharan .

Ethics declarations

Ethics approval and consent to participate.

Not applicable as neither there was any interaction with humans, nor any personal data was collected in this research study.

Consent for publication

Not applicable.

Competing interests

The authors declare no competing interests.

Additional information

Publisher’s note.

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Electronic supplementary material

Below is the link to the electronic supplementary material.

Supplementary Material 1

Rights and permissions.

Open Access This article is licensed under a Creative Commons Attribution 4.0 International License, which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if changes were made. The images or other third party material in this article are included in the article’s Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article’s Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit http://creativecommons.org/licenses/by/4.0/ . The Creative Commons Public Domain Dedication waiver ( http://creativecommons.org/publicdomain/zero/1.0/ ) applies to the data made available in this article, unless otherwise stated in a credit line to the data.

Reprints and permissions

About this article

Cite this article.

Sridharan, K., Sequeira, R.P. Artificial intelligence and medical education: application in classroom instruction and student assessment using a pharmacology & therapeutics case study. BMC Med Educ 24 , 431 (2024). https://doi.org/10.1186/s12909-024-05365-7

Download citation

Received : 26 September 2023

Accepted : 28 March 2024

Published : 22 April 2024

DOI : https://doi.org/10.1186/s12909-024-05365-7

Share this article

Anyone you share the following link with will be able to read this content:

Sorry, a shareable link is not currently available for this article.

Provided by the Springer Nature SharedIt content-sharing initiative

• Medical education
• Pharmacology
• Therapeutics

BMC Medical Education

ISSN: 1472-6920

• Submission enquiries: [email protected]
• General enquiries: [email protected]

Numbers, Facts and Trends Shaping Your World

Read our research on:

Full Topic List

Regions & Countries

• Publications
• Our Methods
• Short Reads
• Tools & Resources

Read Our Research On:

About a third of U.S. workers who can work from home now do so all the time

Roughly three years after the COVID-19 pandemic upended U.S. workplaces, about a third (35%) of workers with jobs that can be done remotely are working from home all of the time, according to a new Pew Research Center survey. This is down from 43% in January 2022 and 55% in October 2020 – but up from only 7% before the pandemic.

While the share working from home all the time has fallen off somewhat as the pandemic has gone on, many workers have settled into hybrid work. The new survey finds that 41% of those with jobs that can be done remotely are working a hybrid schedule – that is, working from home some days and from the office, workplace or job site other days. This is up from 35% in January 2022.

Among hybrid workers who are not self-employed, most (63%) say their employer requires them to work in person a certain number of days per week or month. About six-in-ten hybrid workers (59%) say they work from home three or more days in a typical week, while 41% say they do so two days or fewer.

Related: How Americans View Their Jobs

Many hybrid workers would prefer to spend more time working from home than they currently do. About a third (34%) of those who are currently working from home most of the time say, if they had the choice, they’d like to work from home all the time. And among those who are working from home some of the time, half say they’d like to do so all (18%) or most (32%) of the time.

Pew Research Center conducted this analysis to study how the COVID-19 pandemic has affected the workplace and specifically how workers with jobs that can be done from home have adapted their work schedules. To do this, we surveyed 5,775 U.S. adults who are working part time or full time and who have only one job or who have more than one job but consider one of them to be their primary job. All the workers who took part are members of the Center’s American Trends Panel (ATP), an online survey panel that is recruited through national, random sampling of residential addresses.

Address-based sampling ensures that nearly all U.S. adults have a chance of selection. The survey is weighted to be representative of the U.S. adult population by gender, race, ethnicity, partisan affiliation, education and other categories. Read more about the ATP’s methodology .

Here are the questions used for this analysis, along with responses, and the survey’s methodology .

The majority of U.S. workers overall (61%) do not have jobs that can be done from home. Workers with lower incomes and those without a four-year college degree are more likely to fall into this category. Among those who do have teleworkable jobs, Hispanic adults and those without a college degree are among the most likely to say they rarely or never work from home.

When looking at all employed adults ages 18 and older in the United States, Pew Research Center estimates that about 14% – or roughly 22 million people – are currently working from home all the time.

The advantages and disadvantages of working from home

Workers who are not self-employed and who are teleworking at least some of the time see one clear advantage – and relatively few downsides – to working from home. By far the biggest perceived upside to working from home is the balance it provides: 71% of those who work from home all, most or some of the time say doing so helps them balance their work and personal lives. That includes 52% who say it helps them a lot with this.

About one-in-ten (12%) of those who are at least occasionally working from home say it hurts their ability to strike the right work-life balance, and 17% say it neither helps nor hurts. There is no significant gender difference in these views. However, parents with children younger than 18 are somewhat more likely than workers without children in that age range to say working from home is helpful in this regard (76% vs. 69%).

A majority of those who are working from home at least some of the time (56%) say this arrangement helps them get their work done and meet deadlines. Only 7% say working from home hurts their ability to do these things, and 37% say it neither helps nor hurts.

There are other aspects of work – some of them related to career advancement – where the impact of working from home seems minimal:

• When asked how working from home affects whether they are given important assignments, 77% of those who are at least sometimes working from home say it neither helps nor hurts, while 14% say it helps and 9% say it hurts.
• When it comes to their chances of getting ahead at work, 63% of teleworkers say working from home neither helps or hurts, while 18% say it helps and 19% say it hurts.
• A narrow majority of teleworkers (54%) say working from home neither helps nor hurts with opportunities to be mentored at work. Among those who do see an impact, it’s perceived to be more negative than positive: 36% say working from home hurts opportunities to be mentored and 10% say it helps.

One aspect of work that many remote workers say working from home makes more challenging is connecting with co-workers: 53% of those who work from home at least some of the time say working from home hurts their ability to feel connected with co-workers, while 37% say it neither helps nor hurts. Only 10% say it helps them feel connected.

In spite of this, those who work from home all the time or occasionally are no less satisfied with their relationship with co-workers than those who never work from home. Roughly two-thirds of workers – whether they are working exclusively from home, follow a hybrid schedule or don’t work from home at all – say they are extremely or very satisfied with these relationships. In addition, among those with teleworkable jobs, employed adults who work from home all the time are about as likely as hybrid workers to say they have at least one close friend at work.

Feeling connected with co-workers is one area where many workers who rarely or never work from home see an advantage in their setup. About four-in-ten of these workers (41%) say the fact that they rarely or never work from home helps in how connected they feel to their co-workers. A similar share (42%) say it neither helps nor hurts, and 17% say it hurts.

At the same time, those who rarely or never work from home are less likely than teleworkers to say their current arrangement helps them achieve work-life balance. A third of these workers say the fact that they rarely or never work from home hurts their ability to balance their work and personal lives, while 40% say it neither helps nor hurts and 27% say it helps.

When it comes to other aspects of work, many of those who rarely or never work from home say their arrangement is neither helpful nor hurtful. This is true when it comes to opportunities to be mentored (53% say this), their ability to get work done and meet deadlines (57%), their chances of getting ahead in their job (68%) and whether they are given important assignments (74%).

Most adults with teleworkable jobs who work from home at least some of the time (71%) say their manager or supervisor trusts them a great deal to get their work done when they’re doing so. Those who work from home all the time are the most likely to feel trusted: 79% of these workers say their manager trusts them a great deal, compared with 64% of hybrid workers.

Hybrid workers feel about as trusted when they’re not working from home: 68% say their manager or supervisor trusts them a great deal to get their work done when they’re not teleworking.

Note: Here are the questions used for this analysis, along with responses, and the survey’s methodology .

• Business & Workplace
• Coronavirus (COVID-19)

A look at small businesses in the U.S.

Majorities of adults see decline of union membership as bad for the u.s. and working people, a look at black-owned businesses in the u.s., from businesses and banks to colleges and churches: americans’ views of u.s. institutions, 2023 saw some of the biggest, hardest-fought labor disputes in recent decades, most popular.

1615 L St. NW, Suite 800 Washington, DC 20036 USA (+1) 202-419-4300 | Main (+1) 202-857-8562 | Fax (+1) 202-419-4372 |  Media Inquiries

Research Topics

• Age & Generations
• Economy & Work
• Family & Relationships
• Gender & LGBTQ
• Immigration & Migration
• International Affairs
• Internet & Technology
• Methodological Research
• News Habits & Media
• Non-U.S. Governments
• Other Topics
• Politics & Policy
• Race & Ethnicity
• Email Newsletters

ABOUT PEW RESEARCH CENTER  Pew Research Center is a nonpartisan fact tank that informs the public about the issues, attitudes and trends shaping the world. It conducts public opinion polling, demographic research, media content analysis and other empirical social science research. Pew Research Center does not take policy positions. It is a subsidiary of  The Pew Charitable Trusts .

Copyright 2024 Pew Research Center

Terms & Conditions

Privacy Policy

Cookie Settings

Reprints, Permissions & Use Policy