Learning about social learning in MOOCs: From statistical analysis to generative model

We study user behavior in the courses offered by a major Massive Online Open (MOOC) provider during the summer of 2013. Since social learning is a element of scalable education in MOOCs and is done via online discussion, our main focus is in understanding forum activities. Two salient of MOOC forum activities drive our research: 1. High decline rate: for courses studied, the volume of discussions in the forum declines throughout the duration of the course. 2. High-volume, noisy: at least 30% of the courses produce new discussion threads at that are infeasible for students or teaching staff to read through. , a substantial portion of the discussions are not directly-related. We investigate factors that correlate with the decline of activity in the discussion forums and find effective strategies to classify threads and their relevance. Specifically, we use linear regression models to analyze time series of the count data for the forum activities and make a number of, e. g. , the teaching staff's active participation in the discussion the discussion volume but does not slow down the decline rate. We propose a unified generative model for the discussion threads, which us both to choose efficient thread classifiers and design an effective for ranking thread relevance. Our ranking algorithm is further against two baseline algorithms, using human evaluation from Amazon Turk. The authors on this paper are listed in alphabetical order. For media and coverage, please refer to us collectively, as "researchers from the EDGE at Princeton University, together with collaborators at Boston University Microsoft Corporation. "