The Recommender systems (RSs) are well-established techniques for providing personalized recommendations to users by successfully handling information overload due to unprecedented growth of the web. Context-aware RSs (CARSs) have proved to be reliable for providing more relevant and accurate predictions by incorporating contextual situations of the user. Although, collaborative filtering (CF) is the widely used and most successful technique for CARSs but it suffers from sparsity problem. In this paper, we attempt toward introducing fuzzy trust into CARSs to address the problem of sparsity while maintaining the quality of recommendations. Our contribution is twofold. Firstly, we exploit fuzzy trust among users through fuzzy computational model of trust and incorporate it into context-aware CF (CACF) technique for better recommendations. Secondly, we use fuzzy trust propagation for alleviating sparsity problem to further improve recommendations quality. The experimental results on two real world datasets clearly demonstrate the effectiveness of our proposed schemes.
CITATION STYLE
Linda, S., & Bharadwaj, K. K. (2016). A fuzzy trust enhanced collaborative filtering for effective context-aware recommender systems. In Smart Innovation, Systems and Technologies (Vol. 51, pp. 227–237). Springer Science and Business Media Deutschland GmbH. https://doi.org/10.1007/978-3-319-30927-9_23
Mendeley helps you to discover research relevant for your work.