Identifying Users from Online Interactions in Twitter.
Madeena Sultana, Padma Polash Paul, Marina L. Gavrilova · Trans. Computational Science · 2016
In recent years, the mass growth of online social networks has introduced a completely new platform of analyzing human behavior. Human interactions via online social networks leave big trails of behavioral footprints, which have been investigated by many researchers for the purpose of targeted advertising and business. However, analysis of such online interactions is rarely seen for user identification. The main objective of this paper is to analyze individuals' online interactions as biometric information. In this paper, we investigated how online interactions retain behavioral characteristics of users and how consistent they are over time. For this purpose, we proposed a novel method of identifying users from online interactions in Twitter. Identification performance has been evaluated on a database of 50 Twitter users over five different time periods. We obtained very promising results from experimentation, which demonstrate the potential of online interactions in aiding the authentication process of social network users'.