Using Automatic Detection to Identify Students' Learning Style in Online Learning Environment -- Meta Analysis

Abstract

Numerous studies have been carried out for the past several years concerning the promising method on automatic detection of students' learning style for a better learning adaption. Likewise in this study, we emphasize on presenting the result for the meta-analysis done on previous studies which incorporated the use of literature-based method - narrowing to active and reflective dimensions of Felder and Silverman model via online learning environment. Through the aforementioned method, we managed to critically identify several essential aspects that can benefit and serve as a guideline for implementing an automatic detection of learning style approach in the future. Among the aspects that worth being observed from the presented six studies are online learning platform, relevant features, behavior pattern, and precision. Further discussions on the aspects are presented in the paper.