Are Attributes on Social Media Platforms Usable for Assisting in the Automatic Detection of Identity Deception?

Social Media Platforms (SMPs) allow any person to easily communicate with their friends or the general public at large. People can now be targeted at great scale, most often for malicious purposes. The mere fact that more people are using SMPs exposes more people to various forms of cyber threats such as cyber-bullying. The problem is that many of these cyber-attacks involve some form of identity deception, where the attackers lie about who they are. The solution proposed in this paper is to work towards developing a model for Identity Deception Detection (IDD) on SMPs by identifying and using metadata that is freely available on SMPs. This metadata includes attributes that describes a user account on an SMP. The aim is to use only these attributes, as opposed to the contents of a communication, for determining if people are lying about their identities. By discarding contents, an identity deception detection model can be developed with lower overhead. A prototype is discussed that runs an experiment using the metadata (attributes) that defines the identity of a user on an SMP. The results show promise for further research in developing solutions for assisting with the automatic detection of identity deception.