Learning materials recommendation using good learners' ratings and content-based filtering

The enormity of the amount of learning materials in e-learning has led to the difficulty of locating suitable learning materials for a particular learning topic, creating the need for recommendation tools within a learning context. In this paper, we aim to address this need by proposing a novel e-learning recommender system framework that is based on two conceptual foundations-peer learning and social learning theories that encourage students to cooperate and learn among themselves. Our proposed framework works on the idea of recommending learning materials with a similar content and indicating the quality of learning materials based on good learners' ratings. A comprehensive set of experiments were conducted to measure the system accuracy and its impact on learner's performance. The obtained results show that the proposed e-learning recommender system has a significant improvement in the post-test of about 12.16% with the effect size of 0.6 and 13.11% with the effect size of 0.53 when compared to the e-learning with a content-based recommender system and the e-learning without a recommender system, respectively. Furthermore, the proposed recommender system performed better in terms of having a small rating deviation and a higher precision as compared to e-learning with a content-based recommender system.