EduRecomSys: An Educational Resource Recommender System Based on Collaborative Filtering and Emotion Detection

Abstract

Abstract Due to the large amount of data that is available on the Web, it has become increasingly difficult to locate educational resources that satisfy specific learning needs. Furthermore, the searching process can become increasingly frustrating, time-consuming and little accurate when users do not know how to perform a search. Recommender systems aim at reducing this burden by predicting and recommending users relevant elements of interest. In the educational domain, recommender systems can take advantage of user cognitive states and emotions to generate more personalized recommendations. This work proposes EduRecomSys, an educational recommender system that combines collaborative filtering with emotion detection techniques to suggest users educational resources based on the preferences/interests of other users and the user’s emotion previously detected through face recognition technologies. Likewise, EduRecomSys allows users to retrieve educational resources from multiple sources, including social networks, linked data and learning object repositories. EduRecomSys was evaluated in qualitative and quantitative terms. The qualitative evaluation relied on the participation of three domain experts: a teacher, a pedagogue and a software engineer. The quantitative evaluation was conducted with the help of 20 graduate students. The evaluation results seem encouraging and suggest that EduRecomSys has the potential to provide effective support to the teaching-learning process.