Panayiota (Pani) Kendeou, PhD

This month, we are honored to spotlight Panayiota (Pani) Kendeou, Ph.D., whose work investigates how people learn during reading and how they revise misconceptions when presented with new information. Her team develops AI tools that personalize instruction and AI chatbots to identify and refute misconceptions, with the potential to combat misinformation at scale.

Please join us in celebrating Dr. Kendeou’s innovative contributions to education and data science, and read her answers below!

1. What are your current research interests, and how does AI intersect with your work?

My research focuses on understanding how people learn during reading and revise misconceptions when confronted with new information. AI intersects with my work in at least two ways. First, we develop AI tools that personalize instruction of core skills that support learning, such as inference making. Second, we develop and use AI chatbots that can quickly identify and refute misconceptions, potentially combating misinformation at scale.

2. How do you define Data Science, especially in the context of AI and machine learning?

In my field, Data Science is the systematic approach to extracting insights from educational data to understand how learning happens and why it may fail. The goal is to translate these data-based insights into evidence-based educational practices and interventions that can improve learning outcomes.

3. Can you share an interesting or surprising result you've found in your data?

One of our most interesting findings is that once misconceptions are encoded in memory, they continue to influence learning even after they have been corrected. This challenges the intuitive belief that simply providing correct information is enough to change minds or for new learning to happen.

4. Are there any interesting new Data Science or AI tools, models, or libraries you or your students have been using in your work?

We are currently developing and testing AI chatbots specifically designed for educational misconception correction. Our lab infrastructure incorporates crowdsourcing platforms like Prolific for participant recruitment, enabling large-scale studies of learning and comprehension processes.

5. What are you most excited about in your field with regard to Data Science and AI in the next 5 years?

I am most excited about the potential for personalized, AI-driven interventions that can adapt to how people process information and revise knowledge and beliefs. This could revolutionize how we combat misinformation and support learning in our increasingly mediatized and AI-mediated information ecosystem. I am also excited about integrating AI Literacy in K-12 education in a way that is theory-based, responsible, and ethical.