Trust and Distrust Propagation Models in Social Networks

With the increasing of information overloading in social networks, it is necessary to have a trust model to help the users to collect the reliable information. Users can get reliable information from trusted users. But each user is associated with a few other users and only trust/distrust them. Trust/Distrust propagation is used to predict the unknown relationships among users. Recent researches have more focus on propagation of trust ratings and different models are presented for this purpose. In this paper, we used Direct and Transpose propagation models and investigated the trust and distrust ratings propagation in different modes. In this regard, some hypotheses are proposed and each hypothesis is tested on a real-world data set collected from epinions.com website. The results of experiments show the correctness or incorrectness of the hypothesis and these results can be used to predict the trust/distrust relationship between users.

Keywords:

direct propagation , transpose propagation , trust , distrust propagation