The Effect of Incorporating Good Learners' Ratings in e-Learning Content-Based Recommender System.

Abstract

One of the anticipated challenges of today’s e-learning is to solve the problem of recommending from a large number of learning materials. In this study, we introduce a novel architecture for an e-learning recommender system. More specifically, this paper comprises the following phases i) to propose an e-learning recommender system based on content-based filtering and good learners’ ratings, and ii) to compare the proposed e-learning recommender system with exiting e-learning recommender systems that use both collaborative filtering and content-based filtering techniques in terms of system accuracy and student’s performance. The results obtained from the test data show that the proposed e-learning recommender system outperforms existing e-learning recommender systems that use collaborative filtering and content-based filtering techniques with respect to system accuracy of about 83.28% and 48.58%, respectively. The results further show that the learner’s performance is increased by at least 12.16% when the students use the e-learning with the proposed recommender system as compared to other recommendation techniques.