Ramesh, Arti, et al. "Understanding MOOC discussion forums using seeded LDA." Proceedings of the ninth workshop on innovative use of NLP for building educational applications. 2014.

This study investigates the use of topic models, specifically seeded topic models, to analyze discussion forums in Massive Open Online Courses (MOOCs). By examining forum content, the research aims to uncover insights that can improve student retention and inform instructor interventions. The findings show that features derived from topic analysis are effective in predicting student survival in MOOCs.