Using machine learning to detect fake identities : bots vs humans

Abstract

There is a growing number of people who hold accounts on social media platforms (SMPs) but hide their identity for malicious purposes. Unfortunately, very little research has been done to date to detect fake identities created by humans, especially so on SMPs. In contrast, many examples exist of cases where fake accounts created by bots or computers have been detected successfully using machine learning models. In the case of bots these machine learning models were dependent on employing engineered features such as the ’friend-to-followers ratio’. These features were engineered from attributes, such as ’friend-count’ and ’follower-count’, which are directly available in the account profiles on SMPs. The research discussed in this paper applies these same engineered features to a set of fake human accounts in the hope of advancing the successful detection of fake identities created by humans on SMPs.