Social Recommendation Based on Content and Trust

Report published in the Proceedings of the National Conference on "Education and Research in the Information Society", Plovdiv, May, 2014

This paper present analysis on different recommendation approaches for social networks. The main accent is on content based filtering and trust aware recommendations as new formulas for calculating trust are suggested. The experiments are made on data gathered from the social network Facebook via custom made application, as 3 different approaches are compared – content-based filtering, trust based recommendation and hybrid approach. Results shows that trust calculated from the social activities of the users is good source for recommendation as with the hybrid approach the recall is increased.

Association for the Development of the Information Society, Institute of Mathematics and Informatics Bulgarian Academy of Sciences, Plovdiv University "Paisii Hilendarski"