A Data-Driven Student Model to Provide Adaptive Support During Video Watching Across MOOCs

摘要

MOOCs have great potential to innovate education, but lack of personalization. In this paper, we show how FUMA, a data-driven framework for student modeling and adaptation, can help understand how to provide personalized support to MOOCs students, specifically targeting video watching behaviors. We apply FUMA across several MOOCs to show how to: (i) discover video watching behaviors that can be detrimental for or conductive to learning; (ⅱ) use these behaviors to detect ineffective learners at different weeks of MOOCs usage. We discuss how these behaviors can be used to define personalized support to effective MOOC video usage regardless of the target course.