Predicting Student Performance in an Embodied Learning Environment

Abstract

Implementing machine learning techniques is receiving considerable attention in the educational technology research field. Different systems and techniques were proposed to predict student performance and gain insights regarding their learning needs. However, to the best of our knowledge, no previous research studies explored predicting student performance based on their interaction with different modalities in a real classroom context In this paper, we have proposed an adaptive learning engine to recommend embodied activities and interaction modalities according to students learning profile, prior knowledge, and academic performance. We have firstly conducted a comparative study by analyzing two educational datasets. Among five classification algorithms, Random Forest outperformed with 84% as accuracy. Thus, in a second phase, we have explored predicting students' performance with our dataset generated from embodied learning environment. The accuracy of the proposed model using student profile, academic, and behavioral features reached an accuracy of 62%. These results highlighted the potential of implementing machine learning techniques to classify and recommend embodied interaction