Research on Item Model in Content-Based Filtering Recommender Systems

Abstract

With the popularization of the Internet and the development of E-commerce, the information on the Networks has increased greatly and the E-Commerce system’s structure becomes more complicated when it provides more and more choices for users. People all have experienced the feeling of being overwhelmed by the number of new books, articles, and movies coming out each year. Many researchers pay more attention on building a proper tool which can help users obtain personalized resources. Personalized recommender systems are one such software tool in which information retrieve, information filtering, and content-based filtering techniques are used to help users obtain recommendations for unseen items based on their preferences. In this paper, described item models in content-based filtering recommender systems in order to alleviate the information overload issues. The paper presented three item models as following: vector space model representation, probability model representation and improved probabilistic model representation. These item models have their own advantages and disadvantages, and can choose according to specific circumstances.