Research of collaborative filtering algorithm based on the semantic similarity

Item-based Collaborative Filtering algorithms can enhance the scalability problems associated with traditional user-based Collaborative Filtering approaches and avoid the bottleneck of computing user-user correlations by considering the relationships among items. But it still works poor in solving the problem of sparsity, predictions for new Items. In order to resolve efficiently several problems, the paper introduces a collaborative filtering algorithm base on the semantic about similarity structured semantic knowledge about Items. We build domain-special ontology by ontology learning and use wrapper agents to automatically extracting instances,of the ontology classes and semantic properties about Items from web site. Experimental results show that the collaborative filtering algorithm base on the semantic similarity efficiently deals with the problems associated with item-based Collaborative Filtering algorithms as well as improving accuracy.