Tracking Social Networks Events

Online social media represent a fundamental shift of how information is being produced, transferred and consumed. User generated content in the form of blog posts, comments, and tweets establishes a connection between information producers and consumers. Tracking the pulse of the social media outlets enables companies to gain feedback and insight in how to improve and market products better. For consumers, the abundance of information and opinions from diverse sources helps them make more informed decisions. However, the huge level of online interactions leads to permissive usage behaviours, opening the door for viruses, worms, trojan horses and other threats to install and easily spread, without being noticed. Being able to track users activities, organize the retrieved information in a comprehensive way and analyze it can be very useful for several management, engineering and security tasks. This paper proposes a framework to collect social network events and store them in a relational database for posterior analysis. A graphical user interface was developed to allow flexible access to stored information, according to the type of event, thus facilitating the analysis of users behaviours. From a privacy perspective, the proposed framework is not intrusive because it only gathers the actions timestamps and not their complete contents. By computing statistical models over the obtained data, it is possible to define ”normal or typical” usage profiles and detect possible deviations that can be indicative of a compromised user account. Keywords–Monitoring Framework; User Behaviour Modelling; Social Network; Compromised User Account.