Recommending Users in Social Networks by Integrating Local and Global Reputation

A central research theme in the Online Social Network (OSN) scenario consists of predicting the trustworthiness a user should assign to the other OSN members. Past approaches to predict trust relied on global reputation models: they were based on feedbacks about the actions performed by the user in the past and provided for the entire OSN. These models have shown an evident limitation in considering the effects of malicious and fraudulent behaviors, thus making unreliable the feedbacks themselves. In this paper, we propose to integrate global reputation models with a local reputation, computed on the user ego-network. Some experiments, performed on real datasets show that the global reputation is useful only if the size of the user ego-network is small, as for a newcomer. Besides, the integrated usage of global and local reputations leads to predict the expected trust with a very high level of precision.