Fake Account Identification in Social Networks

Nowadays, the human influence often depends on the number of followers that an individual has in his/her own social media context. To this end, the presence of fake accounts is one of the most relevant problems and can potentially have a big impact on many real life and business activities. Fake followers are dangerous for social platforms, since they may alter concepts like popularity and influence, which might yield a strong impact on economy, politics, and society. Thus, it is necessary to devise new methodologies enabling the possibility to identify and characterize fake accounts. This work presents a novel technique to discriminate real accounts on social networks from fake ones. The technique exploits knowledge automatically extracted from big data to characterize typical patterns of fake accounts. We empirically evaluated the proposed technique on the Twitter social network, and achieved significant results in terms of discrimination capabilities.

I. Introduction

Internet and social networks have revolutionized the modern society, and they quite influence the daily routine. In fact, an individual has a virtual life that is often tightly coupled with his/her everyday life. In particular, friendships are established through Facebook, jobs can be found through LinkedIn, and Internet offers more opportunities for social interactions. The world has changed and the progress has allowed people to enter a virtual world, where it is possible to find and do many important things. In the context of social media, influence and popularity of users play a fundamental role; many people follow influential accounts and tend to trust them. What happens if the followed trusted account is fakeƒ Fake accounts include those social network accounts created and sold to users in order to increase their influence and their involvement for different social reasons. However, fake accounts are just one example of "anomalous" accounts that are spreading over social networks.