Profiling MOOCs from viewing perspective

Abstract

We profiled three aspects of MOOCs from the perspective of viewing behaviors, the most prominent and common ones of MOOC learning. They were learner classification, course attraction, teaching order and learning order. Based on viewing behavior data, we provided a non-parametric algorithm to categorize learners, which helped to narrow the scope of finding potential all-rounders, and a method to measure the correlations between teaching order and learning order, which helped to assign teaching contents. Using information entropy, we provided an index to measure course attraction, which integrated the viewing time invested on courses and the number of viewed course videos. This index describes the diminishing marginal utility of repeated viewing and the increasing information of viewing new videos. It has potential to be an auxiliary method of assessing course achievements.