A Topical Crawler for Uncovering Hidden Communities of Extremist Micro-Bloggers on Tumblr

Research shows that microblogging websites such as Tumblr are being misused as a platform to disseminate hate and extremism. We formulate the problem of locating such extremist communities as a graph search problem. We propose a topical crawler based approach performing several tasks: searching for a blogger, computing its similarity against exemplary documents, filtering hate promoting bloggers, navigating through links to other bloggers and managing a queue of such bloggers for social network analysis. We conduct experiments on real world dataset and examine the e↵ectiveness of ’like’ and ’reblog’ features as links between bloggers. Experimental results demonstrates that the proposed solution approach is e↵ective with an F-score of 0.80.