Contrasting the Spread of Misinformation in Online Social Networks

摘要

The emergence of online social networks has revolutionized the way people seek and share information. Nowadays, popular online social sites as Twitter, Facebook and Google+ are among the major news sources as well as the most effective channels for viral marketing. However, these networks also became the most effective channel for spreading misinformation, accidentally or maliciously. The widespread diffusion of inaccurate information or fake news can lead to undesirable and severe consequences, such as widespread panic, libelous campaigns and conspiracies. In order to guarantee the trustworthiness of online social networks it is a crucial challenge to find effective strategies to contrast the spread of the misinformation in the network. In this paper we concentrate our attention on two problems related to the diffusion of misinformation in social networks: identify the misinformation sources and limit its diffusion in the network We consider a social network where some nodes have already been infected from misinformation. We first provide an heuristics to recognize the set of most probable sources of the infection. Then, we provide an heuristics to place a few monitors in some network nodes in order to control information diffused by the suspected nodes and block misinformation they injected in the network before it reaches a large part of the network. To verify the quality and efficiency of our suggested solutions, we conduct experiments on several real-world networks Empirical results indicate that our heuristics are among the most effective known in literature.