An Approach for Dynamic Identification of Online Radicalization in Social Networks

The Online Social Network (OSN) has evolved as a popular platform enabling rich topic-centric interactions and serving as a medium to facilitate online radicalization (Behr et al. 2013). Keeping in view the growing need of uncovering online radicalization, we focus on the information network of Twitter and present an approach for identifying dynamic communities, which arise due to radical topic-centric user interactions. The approach at successive timestamps deploys evolving topic-entity maps along with evolving interaction graphs. We propose Rate of Overlap (ROA(ct)) to determine the similarity among successive community timestamps. We further validate our approach using an open dataset of criminal offences in the city of Denver, Colorado. The approach presented is simple, fast, and effective for dynamic identification of topic-centric communities and, thus, will enable law enforcement agencies to identify hidden radicalization.