Characterizing Dynamic Group Behavior in Social Networks for Cybernetics

Abstract

This chapter is an attempt to characterize users sentiments or opinions for the creation of ad hoc communities over social networks for effective situational awareness. We believe that the mined patterns in user opinions can act as indicators of potential threats in cyberspace. This chapter proposes a novel data-mining approach to identify ad hoc communities and track these communities to effectively identify users and topics that influence the dynamics of a community over time. IntroductionThe recent excrescence of social networking (SN) and social media (SM) as a medium of communication cannot be overlooked primarily for its farreaching applications and outreach. Both SN and SM have developed from a means of casual communication to "virtual glue" that connects individuals over cyberspace. This constantly evolving and dynamic cyber system provides a deluge of data and information that can be exploited to enhance the situational awareness (SA). Existing techniques to achieve SA work by modeling the structure of user communities. These techniques employ standard visualization and quantitative tools to measure correlations between profiles of users within a community and users across communities. Though SA in SN lacks a clear definition and the use of a social network-based SA system is still in the conceptual form, this chapter is aimed at exploiting SN for effective SA. * corresponding author. 105Data Analysis for Network Cyber-Security Downloaded from www.worldscientific.com by NANYANG TECHNOLOGICAL UNIVERSITY on 10/01/15. For personal use only.