Année : 2019
Lieu de publication de l'article :

Résumé de l'article

MOOCs and online courses have notoriously high attrition [1]. Onechallenge is that it can be difficult to tell if students fail to completebecause of disinterest or because of course difficulty. Utilizing aDeep Knowledge Tracing framework, we account for student en-gagement by including course interaction covariates. With these,we find that we can predict a student’s next item response withover 88% accuracy. Using these predictions, targeted interventionscan be offered to students and targeted improvements can be madeto courses. In particular, this approach would allow for gating ofcontent until a student has reasonable likelihood of succeeding.KEYWORDSMOOCS, neural networks, item response, video interactionsACM Reference Format:Kritphong Mongkhonvanit, Klint Kanopka, and David Lang. 2019. DeepKnowledge Tracing and Engagement with MOOCs. In The 9th InternationalLearning Analytics Knowledge Conference (LAK19), March 4–8, 2019, Tempe,AZ, USA.ACM, NewYork, NY, USA, 3 pages. https://doi.org/10.1145/3303772.3303830

Mots-clés

Massive open online course,Item response theory,Attrition (website),