An Unsupervised Method for Discovering How Does Learners Progress toward Understanding in MOOCs

Abstract

Massive Open Online Course (MOOC) seems to expand access to education and it present too many advantages as: democratization of learning, openness to all and accessibility on a large scale, etc. However, this new phenomenon of open learning suffers from the lack of personalization; it is not easy to identify learners’ characteristics because their heterogeneous masse. Following the increasing adoption of learning styles as personalization criteria, it is possible to make learning process easier for learners. In this paper, we extracted features from learners’ traces when they interact with the MOOC platform in order to identify learning styles in an automatic way. For this purpose, we adopted the Felder-Silverman Learning Style Model (FSLSM) and used an unsupervised clustering method. Finally, this solution was implemented to clustered learners based on their level of preference for the sequential/global dimension of FSLSM. Results indicated that, first: k-means is the best performing algorithm when it comes to the identification of learning styles; second: the majority of learners show strong and moderate sequential learning style preferences.