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

TL;DR

This paper explores how neural embedding representations derived from contextual action logs can predict the popularity of student-created artifacts in online learning, outperforming traditional instructor-based features and enabling more inclusive collaborative environments.

Contribution

It introduces a neural embedding approach from action logs to predict artifact popularity, reducing reliance on human labeling and enhancing social learning insights.

Findings

Neural embeddings from action logs best predict artifact popularity.

Instructor-specified features are less predictive than learned embeddings.

Embedding-based predictions enable real-time, inclusive feedback in online learning.

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.