Forum Thread Recommendation for Massive Open Online Courses

Recently, Massive Open Online Courses (MOOCs) have garnered a high level of interest in the media. With larger and larger numbers of students participating in each course, finding useful and informative threads in increasingly crowded course discussion forums becomes a challenging issue for students. In this work, we address this thread overload problem by taking advantage of an adaptive feature-based matrix factorization framework to make thread recommendations. A key component of our approach is a feature space design that effectively characterizes student behaviors in the forum in order to match threads and users. This effort includes content level modeling, social peer connections, and other forum activities. The results from our experiment conducted on one MOOC course show promise that our thread recommendation method has potential to direct students to threads they might be interested in.