Relational Distance-Based Collaborative Filtering for E-Learning

Recommender systems for e-learning need to consider the specific demands and requirements and to improve the ´educational aspects´ for the learners. In this paper, we present a novel hybrid recommender system called RelationalCF, which integrates learners and learning items information into a collaborative filtering framework by using relational distance computation approaches. Our experiments suggest that the effective combination of various kinds of learning information based on relational distance approaches provides improved accurate recommendations than other approaches.