Identifying Student Leaders from MOOC Discussion Forums through Language Influence

Abstract

Identifying and understanding the motivations of student leaders from Massively Open Online Course (MOOC) discussion forums provides the key to making the online learning environment engaging, collaborative, and instructive. In this paper, we propose to identify student leaders solely based on textual features, or specifically by analyzing how they influence other students’ language. We propose an improved method of measuring language accommodation based on people’s choice of words given a semantic topic of interest, and show that student leaders indeed coordinate other students’ language usage. We also show that our proposed method can successfully distinguish student leaders from the two MOOC discussion forum datasets.