Learning Fuzzy User Models for News Recommender Systems

Online news reading has become a widely popular way to read news articles from news sources around the globe. With the enormous amount of news articles available, users are easily overwhelmed by information of little interest to them. News recommender systems help users manage this flood by recommending articles based on user interests rather than presenting articles in order of their occurrence. In this paper, we propose an approach using evolutionary algorithm to learn fuzzy models of user interests used for recommending news articles gathered from RSS feeds. These models are dynamically updated by track the interactions between the users and the system. The system is ontology-based, in the sense that it considers concepts behind terms instead of simple terms. The approach has been implemented in a real-world prototype newsfeed aggregator with search facilities called iFeed. Experimental results show that our system learns user models effectively by improving the quality of the recommended articles.