The proposed system represents based on groups -based Faith

The rapid growth of the World Wide Web, is an overload of information while facilitate access to a variety of information creates a new problem. We will not be kept condition in which the amount of information to make decisions, selection or update their information on a particular topic. Bidder systems have been proposed as an effective solution to this problem. One of the most important methods for implementation of bidder systems is the use of the concept of trust between people, especially in social networks. Trust-based recommender systems can be more than traditional recommender systems such as filters, orrelation, and provide more personalized recommendations. However, problems still remain such as scattering data, scalability, and accuracy. In this thesis, is presented a new method for the proposed system based on the trusted group. In this model, each party can find a group or individual's confidence. Groups are formed based on the similarity between individuals, and then registration per person based on two factors, comes from the degree of similarity between the group and the group's confidence. In this model, the relationship between the groups helping to develop the relationship between paid users, this way, users become acquainted with people who had never had any knowledge about it. The results of implementation showed when we use a combination of trust and propose a similarity, will improve performance of Proposal. Our results also showed that in the absence of adequate information such as the relationship between users with low ratings low, this could propose very well for more users.

کلیدواژه ها:

Systems bidder ، trust ، group ، network reliability