Simulating a trust-based service recommender system for decentralised user modelling environment

Trust and reputation mechanisms are often used in peer-to-peer networks, multi-agent systems and online communities to differentiate among members of the community as well as to recommend service providers. Although different users have different needs and expectations in different aspects of the service providers, few exiting trust models use differentiated trust values for judging different aspects of service providers. We have proposed a multi-aspect trust model where each user has two sets of trust values: 1) trust on different aspects of the quality of service providers; 2) differentiated trust on the recommendations provided by other users for each of these aspects. This trust model is used to recommend service providers in a decentralised user modelling system where agents have different preference weights in three different criteria of service providers. The paper focuses on the evaluation of the approach via a simulation on a large real social network. The results show that the trust model allows agents to learn from experience to find good service providers by using recommendations from their friends and that the model is robust with respect to colluding malicious agents.