Date and time: Friday 11 December 2026, 12:00-13:00 CET (arrive at 11:45 for FREE LUNCH*)
Speaker: Prof Ryan Baker, Adelaide University
Title: AI Project Feedback with JeepyTA: Do Students Actually Learn?
Where: Digital Futures hub, Osquars Backe 5, floor 2 at KTH main campus OR Zoom
Directions: https://www.digitalfutures.kth.se/contact/how-to-get-here/
OR
Zoom: https://kth-se.zoom.us/j/69560887455
*To get a FREE LUNCH, you need to register — first come, first served. Maximum 50 participants.
The hub will be open 30 minutes before and after the event for those who wish to stay longer.
Host: Olga Viberg, oviberg@kth.se
Bio: Ryan Baker is Professor of Artificial Intelligence and Education at Adelaide University and Director of the Penn Center for Learning Analytics at the University of Pennsylvania. Baker has developed models that can automatically detect student engagement in over a dozen online learning environments, and led the development of an observational protocol and app for field observation of student engagement that has been used by over 150 researchers in 7 countries.
Predictive analytics models he helped develop have been used to benefit over two million students, over a hundred thousand people have taken MOOCs he ran, and he has coordinated longitudinal studies that spanned over a decade.
Baker was the founding president of the International Educational Data Mining Society, is Associate Editor of the Journal of Educational Data Mining, was the first technical director of the Pittsburgh Science of Learning Center DataShop, currently serves as Co-Director of the JeepyTA learning platform, and founded two Masters degree programs in Learning Analytics.
Baker has co-authored published papers with over 600 colleagues and has been cited over 40,000 times.
Abstract: Prior research shows that AI-generated feedback can improve student performance on essays and projects. However, the goal of education is not to improve performance but to produce sustained learning. In this talk, I will discuss our work to study how students use and learn from AI feedback in the JeepyTA discussion forum platform in and across multiple courses at the University of Pennsylvania. This feedback was designed to involve deeper aspects of project work rather than more surface-level aspects such as grammar or clarity.
I will discuss our research investigating how students use feedback, the impacts of feedback on their current assignment, on future assignments in the same course, and on similar assignments in future courses. We find evidence that JeepyTA’s feedback led to better performance both in the short-term and on subsequent assignments in the same course, but did not transfer to a subsequent course.
