A Heuristic Recommendation Method Based on Contextual Social Network

摘要

To increase the precision in recommendation, a heuristic recommendation method based on contextual social network is proposed. A contextual social network is constructed based on basic social network, including contextual information such as the trust relationship, user role, user profile and user preference. A heuristic method combined with collaborative filtering is introduced for recommendation on the basis of the comprehensive trust relationship obtained from the contextual social network. To evaluate the performance of the algorithm, comparison experiments were conducted on real world dataset. The experimental results show that the method can get better time efficiency and recommendation accuracy compared with others.