A Proactive Personalized Mobile News Recommendation System
Kam Fung Yeung, Yanyan Yang · 2010
Recommendation Systems have become an important research area in mobile computing. Although various recommendation systems have been developed to help users to deal with information overload, few systems focus on proactive information recommendation. This paper presents a news recommender system that proactively pushes just-in-time personalized news articles to mobile users based on user's contextual information as well as news content. User's information needs are estimated based on Bayesian network technique. An Analytic Hierarchy Process (AHP) Model, which supports both Content-based filtering and Collaborative filtering, is developed to rate the relevance of news articles. The weight of contexts (criteria) is automatically adjusted via individual-based and/or group-based (group decision making) assignment. The experiments show that the system can push relevant news to mobile users.