Research And Implementation Of Book Recommendation System Based On Multi-view Hashing

With the development of Internet, digital library has gained wide attention. Book recommendation system plays an important role in digital library. In this paper, we propose to apply the multi-view hashing algorithm in book recommendation system, by integrating users’ action data from different sources. This can make the recommendation system more efficient on the premise of the higher accuracy, in the context of big data in digital library.The main contributions of this paper are as follows:First, research one kind of hashing code generating algorithm which makes use of users’action data from different sources, that is, multi-view hashing algorithm. This algorithm can not only preserve similarity between users, but also integrate users’ action data from different sources. On the other hand, the generating hash codes can be used to search similar users in recommendation system, which can improve the efficiency.Second, construct the book recommendation system which is based on the multi-view hashing algorithm, which consist of the data collecting engine, the algorithm engine and the recommendation engine. We do some experiments in the book recommendation system which is based on multi-view hashing algorithm. The experimental results show that the multi-view algorithm is more efficient, while still has a higher accuracy.