How Far are we in Trust-Aware Recommendation?

TitleHow Far are we in Trust-Aware Recommendation?
Publication TypeConference Paper
Year of Publication2011
AuthorsShi, Y, Larson, MA, Hanjalic, A
Refereed DesignationRefereed
Conference NameECIR '11: Proceedings of the 33rd European Conference on Information Retrieval
Conference LocationDublin, Ireland
KeywordsRecommender systems, social trust, trust-aware recommendation

Social trust holds great potential for improving recommendation and much recent work focuses on the use of social trust for rating prediction, in particular, in the context of the Epinions dataset. An experimental comparison with trust-free, naïve approaches suggests that state-of-the-art social-trust-aware rec-ommendation approaches, in particular Social Trust Ensemble (STE), can fail to isolate the true added value of trust. We demonstrate experimentally that not only trust-set users, but also random users can be exploited to yield recommen-dation improvement via STE. Specific users, however, do benefit from use of social trust, and we conclude with an investigation of their characteristics.