Research on collaborative filtering recommendation method of online learning resources based on learner model

Abstract

Online learning plays an increasingly important role in the field of education for its advantages of solid flexibility, openness, and richness. However, it also faces problems such as information explosion and resource overload, which makes it difficult for learners to obtain personalized learning resources timely and accurately and to complete learning efficiently. Learning resource recommendation is one of the critical countermeasures to solve the above problem. The current recommendation of learning resources is mainly based on the traditional collaborative filtering recommendation method and content-based recommendation method, which do not fully consider learners' characteristics resulting in unsatisfactory effects. A collaborative filtering recommendation method for online learning resources is proposed based on a traditional collaborative filtering algorithm and combined with research in the learner modeling community. This method incorporates learners' characteristics and learning behaviors into recommendation calculations making the recommended learning resources better match learners' individual needs. This study implemented the proposed method based on an influential online teachers' professional development community in China. The results show that the performance of recommendation is significantly higher than the traditional recommendation method.