Multi Relational and Social Influence Model for Predicting Student Performance in Intelligent Tutoring Systems ITS

Abstract

Recent studies have shown that Matrix Factorization (MF) method, deriving from recommendation systems, can predict student performance as part of Intelligent Tutoring Systems (ITS). In order to improve the accuracy of this method, we hypothesize that taking into account the mutual influence effect in the relations of student groups would be a major asset. This criterion, coupled with those of the different relationships between the students, the tasks and the skills, would thus be essential elements for a better performance prediction in order to make personalized recommendations in the ITS. This paper proposes an approach for Predicting Student Performance (PSP) that integrates not only friendship relationships such as workgroup relationships, but also mutual influence values into the Weighted Multi-Relational Matrix Factorization method. By applying the Root Mean Squared Error (RMSE) metric to our model, experimental results from KDD Challenge 2010 database show that this approach allows to refine student performance prediction accuracy.

Multi-relational Matrix Factorization Approach for Educational Items Clustering

“…Nevertheless, the Matrix Factorization technique has encountered several improvements such as: MRMF (Multi-Relational Matrix Factorization) [14], WMRMF (Weighted Multi-Relational Matrix Factorization) [15], So-WMRMF (Social Weigthed Multi-Relational Matrix Factorization) [16], Emo -WMRMF (Emotional Weigthed Multi-Relational Matrix Factorization) [15], SoEmo-WMRMF (Socio-Emotional Weigthed Multi-Relational Matrix Factorization) [17]. These approaches generally try to draw on several domain relationships.…”

“…In equation ( 1 where each row i is a vector containing F latent factors describing the task i . [16]. The prediction of the performance of S students for i task to be performed is given by the equation ( 2):…”