Snippet Generation for MOOC discussion forums

Abstract

Massive Open Online Course (MOOC) platforms such as Coursera, edX and Udacity have begun to integrate education technology and learning analytics applications to let instructors effectively manage their class and collect feedback on their class performance. A key aspect of MOOC class management involves two-way instructor-student interaction via discussion forum to catalyse learning. MOOC instructors require tools to manage discussion forum due to information overload.

In this project, we address this problem by proposing a machine learning based system to summarise discussion threads based on their novelty and growth rate.

Members