Generation of web recommendations using implicit user feedback and normalised mutual information
International Journal of Knowledge and Web Intelligence
Hi-index | 0.00 |
The key of personalized recommendation system is to develop a user profile that describes the user's interests. We propose a method to establish the user profile based on Chinese Library Classification (CLC) and feedback behavior. The user interest profile is initialed by CLC, using its thesaurus to describe the user's interest. Then the feedback of user is classified and used, which allows us adjust the user's profile, having the user participate in as little as possible. Finally, based on the above ideas, we develop a document recommend system.