MOOC performance prediction and analysis via Bayesian network and Maslow’s hierarchical needs theory

Abstract

ABSTRACT Nowadays, Massive Open Online Courses (MOOC) has been gradually accepted by the public as a new type of education and teaching method. However, due to the lack of timely intervention and guidance from educators, learners’ performance is not as effective as it could be. To address this problem, predicting MOOC learners’ performance and providing them with timely interventions have become an indispensable part for the MOOC learning. However, current MOOC performance prediction methods cannot provide us with interpretable prediction results and cannot further help us to provide learners with targeted intervention strategies. To this end, we adopt the framework of Bayesian Network (BN) and then constructed an MOOC Performance Prediction BN (MPBN), which provides us with a graphical explanation of how learners’ demographical and learning behavior characteristics affect their performance. Besides, since the productive MOOC learners tend to be driven by their inner goals, we further use Maslow’s hierarchical needs theory to construct several indicators, by which to analyze the prediction of MPBN and then propose the appropriate intervention strategies.