Using Discourse Signals for Robust Instructor Intervention Prediction

TL;DR

This paper demonstrates that incorporating automatically extracted discourse relations from student posts enhances the accuracy and robustness of predicting instructor interventions in MOOC discussion forums, outperforming previous feature-rich models.

Contribution

Introducing PDTB relation-based discourse features into a supervised classifier significantly improves instructor intervention prediction in MOOCs, enhancing generalization across disciplines.

Findings

Discourse relation features improve prediction accuracy.

Models become less dependent on domain-specific vocabulary.

Performance gains observed across 14 diverse MOOC courses.

Abstract

We tackle the prediction of instructor intervention in student posts from discussion forums in Massive Open Online Courses (MOOCs). Our key finding is that using automatically obtained discourse relations improves the prediction of when instructors intervene in student discussions, when compared with a state-of-the-art, feature-rich baseline. Our supervised classifier makes use of an automatic discourse parser which outputs Penn Discourse Treebank (PDTB) tags that represent in-post discourse features. We show PDTB relation-based features increase the robustness of the classifier and complement baseline features in recalling more diverse instructor intervention patterns. In comprehensive experiments over 14 MOOC offerings from several disciplines, the PDTB discourse features improve performance on average. The resultant models are less dependent on domain-specific vocabulary, allowing them to better generalize to new courses.