Identifying Student Leaders from MOOC Discussion Forums through Language Influence

Identifying and understanding the motiva-tions of student leaders from Massively Open Online Course (MOOC) discussion forums provides the key to making the on-line learning environment engaging, col-laborative, and instructive. In this pa-per, we propose to identify student lead-ers solely based on textual features, or specifically by analyzing how they influ-ence other students ’ language. We propose an improved method of measuring lan-guage accommodation based on people’s choice of words given a semantic topic of interest, and show that student leaders in-deed coordinate other students ’ language usage. We also show that our proposed method can successfully distinguish stu-dent leaders from the two MOOC discus-sion forum datasets. 1