Time Really Matters: Revisiting Forum Participation Patterns in MOOCs

• In Event: Poster Session 6
  In Poster Session: Insights on Technologies + Pedagogies (K–12, Higher Education, Massive Open Online Courses)

Abstract

Active forum participation positively relates to learner achievement in Massive Open Online Courses (MOOCs) in a way that more posts over time yield better performance. However, previous research overlooks learner participation is of temporal variation and course attritions are gradual in MOOCs. Therefore, this explorative research applies educational data mining techniques (i.e., longitudinal k-means cluster algorithm) to investigate temporal patterns of forum participation in MOOCs and their influence on learner performance. The research validates temporal patterns of forum participation are more accurate than the numerical convergence of overall forum posts to differentiate learner performance. Learners persistently engaged in the discussion forum are more likely to achieve more in MOOCs. Empirically, the longitudinal k-means cluster algorithm is promising in educational research.

Authors

• Hengtao Tang, The Pennsylvania State University

• Wanli Xing, Texas Tech University