From Tweets to Intelligence: Understanding the Islamic Jihad Supporting Community on Twitter

Abstract

ISIS’ ability to build and maintain a large online community that disseminates propaganda and garners support continues to give their message global reach. Although these communities contain trained media cadre, recent literature suggests that large numbers of “unaffiliated sympathizers” who simply retweet or repost propaganda explain ISIS’ unprecedented online success [1, 2]. Tailored methodologies to detect and study these online threat-group-supporting communities (OTGSC) could help provide the understanding needed to craft effective counter-narratives however continued development of these methods will require collaboration between data scientists and regional experts. We illustrate the potential of this partnership using two ongoing projects at the Center for Computational Analysis of Social and Organizational Systems (CASOS) at Carnegie Mellon University. First we present the CASOS Jihadist Twitter Community (CJTC), an online community of over 15,000 Twitter users that support one or more of the Islamic extremist groups engaged in the ongoing conflicts in Northern Iraq and Syria. We briefly discuss the methods used to detect and monitor these communities and highlight forms of information that can be extracted from them. We then present an active social botnet that attempts to elevate the social influence of users supportive to Jabhat al-Nusra’s agenda. In each case we highlight the ability of these methods to incorporate regional expertise for better performance and recommend future research.