Learning Resource Recommendation Research Based On Collaborative Filtering

With the rapid popularity of computers and Internet, information technology systems is used in people’s daily life gradually and changing the way people of gaining information now. Also the Internet makes online learning more convenient and getting rapid growth. However the problem of information overload is becoming more and more serious.The platforms of learning resource increase. The type of learning resource is becoming more diverse. Nowadays, personalized recommendation of learning resources has become a new trend of the world in the field of e-leaning. It’s helpful to analyze user’s interest and recommend him learning resources which may help his learning. Personalized recommendation has been already widely used in the field of electronic commerce. Nowadays researchers begin to explore personalized recommendation in the field of education.The issue of this paper is to study the question of learning resources recommendation. A learning resource recommendation method combining user sequential interaction with collaborative filtering has been proposed in this paper. This method not only considers the data of users’ rate, but also uses the influence among users mining by data of comment and reply, so that we can get value of users’ interests for the item by users’ history activity. This method optimizes the user-based collaborative method and is not limited to the type of learning resources and social network, so it can be used for learning resources recommendation universally. The experiment results on TED dataset show that the proposed method outperforms user-based CF and item-based CF on both precision and recall.The main content of this paper consists of four parts. The first part summarizes the works of domestic and foreign research and analyzing the characteristics of current e-learning. Second part elaborates the related concepts and recommendation technology. Then, the next part introduces the proposed method of this paper in detail and shows experiment results. The final part summarizes this article’s innovation and future work.