Qualitative research in an age of AI

by | Sunday, April 23, 2023

Qualitative data can be extremely rich, complex and insightful, allowing us to uncover the complexities of human experiences, perceptions, and interactions.

It can also be complicated and messy. And the way we make sense of it is through the one-two punch of thematic coding and inter-rater reliability. Thematic coding allows us to systematically identify key patterns and themes in the data, and allows us to uncover crucial insights that shape our understanding of the topic at hand. Thematic coding, however, can be subjective. One way of minimizing subjectivity is inter-rater reliability. It’s like a reality check for our coding, making sure we’re not letting our own biases cloud our judgement.

More specifically, Inter-rater reliability is a measure of agreement between two or more raters who are coding or rating the same qualitative data. It is often reported as Cohen’s Kappa, a statistical measure that compares the level of agreement between two raters to the level of agreement expected by chance. It can also be reported more simply by just as a percentage agreement.

Now most qualitative research is done by humans. But with the rise of these larger language models a fair question to ask is:

What role can generative AI play in qualitative research?

So I tried out this little experiment, with an interview that we had conducted with Chris Dede. This was the same interview that I had written about earlier, the one that ended up as both an article and a podcast episode. More details about both with links can be found at: A chat about GPT3 and other forms of alien intelligence

As a test I took the transcript of our conversation with Chris and dumped it into anysummary.app, a website that summarizes websites, articles and more. I then created a custom prompt, essentially saying

Take this interview with Chris Dede. Identify 5 key themes in the interview, explain each of them in 3-5 sentences, and, finally select some quotes from the interview that exemplify these themes.

Below is what it came up with. And I do think this is pretty good. Again this is not coding / thematic analysis at a very fine-grained level, but for a first pass, from a freemium website (I just used the free version) it is not too bad, especially if you compare it to the article we wrote based on our interview.

This makes me wonder, just how these AI tools are going to change qualitative research? Should we be ready to have qualitative data coded by AI coders? How soon before we see journal articles reporting Cohen’s Kappa for data that has been coded by humans AND AI systems?

I am pretty sure the day is not too far off.


Anyway here are the themes, explanations and quotes that the AI system came up with from the Chris Dede Interview:

  1. Definition of Intelligence: The transcript explores multiple definitions of intelligence, including whether AI possesses intelligence and what constitutes as strong intelligence. Chris Dede notes that “if you told Goldilocks and the Three Bears to generative ai, it would probably now understand in contrast to the 1980s that this is not a factual story” and that “knowledge, information processing, all of those things are deeply embodied in our bodies in the broader cultural matrix, in the broader social matrix.”
  2. Generative AI: The transcript discusses the concept of generative AI, which is AI that synthesizes things from available resources, resulting in performances that were previously thought to be limited to human beings. Dede explains that “AI does not have that kind of intelligence” and that “generative AI would be completely lost and at sea” without the necessary resources.
  3. Education and AI: The transcript explores the role of AI in education, including developing new educational systems and policies that support transformation. Dede notes that “it’s an exciting time to be in the era of generative ai, which is a major advance in the field” and that “his interests are in developing new types of educational systems to meet the opportunities and challenges of the 21st century.”
  4. Science Fiction: The transcript references science fiction as a source of nuanced discussions on intelligence augmentation and AI-human combinations. Dede notes that “the really nuanced discussions of intelligence augmentation IA have come out of science fiction” and that “if you look at Star Trek, the next Generation, you’ve got data, the Android, who is in fact an AI-based machine, and you’ve got the card, the captain, who is the wise human being.”
  5. Hype Cycles of AI: The transcript acknowledges the cyclical nature of hype surrounding AI and the disappointment that can come with it. Dede notes that he has “lived through many cycles of advances in AI and been impressed by the progress” and that “we rarely never stick to the script” when it comes to utilizing AI in education.

Extended quotes:

  1. On the definition of intelligence: “if you told Goldilocks and the Three Bears to generative ai, it would probably now understand in contrast to the 1980s that this is not a factual story” and “knowledge, information processing, all of those things are deeply embodied in our bodies in the broader cultural matrix, in the broader social matrix.”
  2. On generative AI: “AI does not have that kind of intelligence” and “generative AI would be completely lost and at sea” without the necessary resources.
  3. On education and AI: “it’s an exciting time to be in the era of generative ai, which is a major advance in the field” and “his interests are in developing new types of educational systems to meet the opportunities and challenges of the 21st century.”
  4. On science fiction: “the really nuanced discussions of intelligence augmentation IA have come out of science fiction” and “if you look at Star Trek, the next Generation, you’ve got data, the Android, who is in fact an AI-based machine, and you’ve got the card, the captain, who is the wise human being.”
  5. On hype cycles of AI: “I’ve lived through many cycles of advances in AI and been impressed by the progress” and “we rarely never stick to the script” when it comes to utilizing AI in education.

Postscript: Some great resources for next steps here

A few randomly selected blog posts…

Introducing India…

I had been invited to the Second Annual Internationalizing Michigan Education Conference: Building Bridges from Michigan to the World to speak about India. The title of my presentation was Learning about India, the world’s largest democracy. I was assisted in this by...

Academic publishing, a changing world

A few months ago I had posted a note about Harvard faculty considering and passing a resolution to freely publishing all their scholarship online (see this and this). Now it turns out that faculty at the Stanford University, School of Education have gone the same...

On taking beautiful risks

On taking beautiful risks

Dr. Ronald Beghetto, Professor of Educational Psychology in the Neag School of Education, University of Connecticut, is an internationally recognized expert on creative thought and action in educational settings. He is a Fellow of the American...

Kenya sings India for Pangea Day

NYTimes technology columnist, David Pogue, has a recent blog entry about Pangea Day, a global film festival coming up in a few days. As he says in his note: Pangea Day endeavors to bring the world together and promote understanding and tolerance through film. Over...

The distance education revolution

TCRecord this week features an article by Gary Natriello titled Modest Changes, Revolutionary Possibilities: Distance Learning and the Future of Education. As the abstract says In this essay, I take stock of the developments shaping distance learning and consider the...

Mindfulness & Creativity: New article

Mindfulness & Creativity: New article

Mindful and Creative: Building Educational Systems for Individual and Community Wellbeing In a technology-immersed world awash in distraction, stress, and often, distress—all of which can affect creativity and wellbeing—mindfulness is increasingly becoming a valuable...

Rate of change of technology

I just stumbled upon this image from a 1950 issue of Popular Mechanics. The tag line below the image says: Because everything in her home is waterproof, the housewife of 2000 can do her daily cleaning with a hose. Though it is easy to make fun of this image it can be...

David Zola, Educator Extraordinaire

David Zola, Educator Extraordinaire

A teacher affects eternity—Henry Adams I remember the first time I saw David Zola teach. He was on stage in front of 200+ undergraduate students with a plastic cup of wine in his hand. The wine had been poured for him by a teaching assistant from a bottle hidden in a...

About face

I love finding interesting faces. I am not speaking of the ones on people (though I like interesting ones there as well) but rather the unexpected faces we find in things around us. I have been doing this for a while now and have a flickr set devoted to this. Here are...

1 Comment

  1. techylist

    Interesting blog post. I’m a qualitative researcher myself and I find it really interesting to read about the different ways that AI is being used in qualitative research.

    Reply

Leave a Reply to techylist Cancel reply

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