Main Article Content
Online social networks are nowadays one of the most effective and widespread tools used to share information. In addition to being employed by individuals for communicating with friends and acquaintances, and by brands for marketing and customer service purposes, they constitute a primary source of daily news for a significant number of users. Unfortunately, besides legit news, social networks also allow to effectively spread inaccurate or even entirely fabricated ones. Also due to sensationalist claims, misinformation can spread from the original sources to a large number of users in a very short time, with negative consequences that, in extreme cases, can even put at risk public safety or health.
In this work we discuss and propose methods to limit the spread of misinformation over online social networks. The issue is split in two separate sub-problems. We first aim to identify the most probable sources of the misinformation among the subset of users that have been reached by it. In the second step, assuming to know the misinformation sources, we want to locate a minimum number of monitors (that is, entities able to identify and block false information) in the network in order to prevent that the misinformation campaign reaches some “critical” nodes while maintaining low the number of nodes exposed to the infection.
For each of the two issues, we provide both heuristics and mixed integer programming formulations. To verify the quality and efficiency of our suggested solutions, we conduct experiments on several real-world networks. The results of this extensive experimental phase validate our heuristics as effective tools to contrast the spread of misinformation in online social networks.
Regarding the source identification step, our approach showed success rates above 80% in most of the considered settings, and above 60% in almost all of them.
With respect to the second issue, our heuristic proved to be able to obtain solutions that exceeded (in terms of number of required monitors) the ones obtained through our MILP-based approach of more than 20% in only few test scenarios. Our heuristics for both problems also proved to outperform significantly some previously proposed algorithms.