Informatica

In this paper, we propose a novel trust inference framework in the web-based scenarios which are assumed to have a Web of Trust pre-established, and take the contexts of the trust relationships into account when inferring the recommendation trust. For alleviating the problem of sparse matrix in the Web of Trust, we also incorporate the users’ profile and relationship information on the associated social networks into the framework. Based on the Web of Trust established in the discussed web-based scenario (i.e. epinions.com in this paper), and the social relationship information in the associated social networks, the users are classified into four classes. Then different information is used to infer the users’ recommendation trust value based on the classifications. The simulation experiments show that our approach has good coverage of inferred trust values, and the accurate rate of the predicted trust relationship is higher than the traditional PCC (Pearson Correlation Co-efficiency). According to the computation results of adjusted parameters, it can be concluded that the threshold which is used to filter the inferred trust values can be removed, i.e. all the inferred trust values should be kept.