Beyond learners' interest: Personalized paper recommendation based on their pedagogical features for an e-learning system

Abstract

Delivering personalized recommendations for e-learning is different from that in many other domains (i.e. e-commerce, news, etc.) in that we should not only consider users' interest, but also their pedagogical features such as their learning goals, and background knowledge etc. To attack this problem, in this paper in the context of recommending research papers for learners, we introduce the notion of pedagogy-oriented similarity measurement and propose two pedagogy-oriented recommendation techniques: model-based and hybrid recommendations. To compare these two techniques, we carried out an experiment using artificial learners. Experiment results are encouraging, showing that hybrid collaborative filtering, which can lower the computational costs will not compromise the overall performance of the recommender system. In addition, as more and more learners participate in the learning process, both learner and paper models can better be enhanced and updated, which is especially desirable for web-based learning systems. © Springer-Verlag Berlin Heidelberg 2004.