"Unsupervised Representations Predict Popularity of Peer-Shared Artifacts in an Online Learning Environment"

​Fourth-year doctoral student Renzhe Yu is first author of a new preprint analyzing student interaction in online learning. The article won a Best Paper Honorable Mention at the inaugural Conference on Educational Data Science in 2020 (link).
 
The title of the article is “Unsupervised Representations Predict Popularity of Peer-Shared Artifacts in an Online Learning Environment.”
 
Co-authors are UC Berkeley doctoral candidate John Scott and Associate Professor Zachary A. Pardos.
 
Yu is specializing in Language, Literacy, and Technology. His research interests include learning analytics, learning sciences, instructional design, and computational modeling. He is focusing on advanced computational methods to model and decipher student learning processes from the rich data available in various digital learning environments, with the goal of improving instructional design based on such empirical evidence. Professor Mark Warschauer serves as Yu’s advisor.

​Abstract
 
In online collaborative learning environments, students create content and construct their own knowledge through complex interactions over time. To facilitate effective social learning and inclusive participation in this context, insights are needed into the correspondence between student-contributed artifacts and their subsequent popularity among peers. In this study, we represent student artifacts by their (a) contextual action logs (b) textual content, and (c) set of instructor-specified features, and use these representations to predict artifact popularity measures. Through a mixture of predictive analysis and visual exploration, we find that the neural embedding representation, learned from contextual action logs, has the strongest predictions of popularity, ahead of instructor's knowledge, which includes academic value and creativity ratings. Because this representation can be learnt without extensive human labeling effort, it opens up possibilities for shaping more inclusive student interactions on the fly in collaboration with instructors and students alike.