A Distributed Trust-based Recommendation System on Social Networks英文资料.pdf

A Distributed Trust-based Recommendation System on Social Networks Karan Sarda, Priya Gupta, Debdoot Mukherjee, Smruti Padhy, Huzur Saran Department of Computer Science and Engineering Indian Institute of Technology, Delhi ABSTRACT Such evidence motivates the use of social networks to drive In everyday life, we seek suggestions from people we know a trust-based recommendation system. The real life situation that we want to model can be illus- for deciding the best place to buy a particular good or ser- vice. In this work, we put forth a framework of an automated trated with the following example. Say, for instance, distributed recommendation system on a social network that Alice wants to buy a new camera and seeks advice from her exploits the widely studied concept of , to get person- friends. They respond with their shop preferences, if they alized responses. The main contribution of our model is to have any, or else they further ask their friends about the best combine two forms in which trust is perceived, the camera shop in town and get back to Alice. Finally, Al- and domain-expertise based , to effi- ice receives many recommendations from friends or friends- ciently propagate a query on a social network. We empiri- of-friends and so on. After assessing the recommendations based on how much faith she has in the recommender and cally validate the role of trust in online social networks by crawling the online social networking site and eval- the recomme