Searching for a Virtual Needle in a Cyber-Stack: Identifying Radical Content in Online Discussion Forums

• In Event: Hate is in the Air: Defining, Identifying and Understanding Hate Speech and Radicalization Speech in Cyberspace

Abstract

Counter-extremist agencies are faced with the challenge of identifying radical content on the ever-growing Web. Researchers have hypothesized a number of ways to detect online traces of hatred, yet this area of inquiry is in its infancy. As such, we have developed what we believe is a novel algorithm, titled Sentiment-based Identification of Radical Authors (SIRA), to quantify an individual’s online activity that may be deemed as “extreme” based on their collective posts within a discussion forum. We used an array of computational techniques to identify the most radical users across approximately 1 million posts and 26,000 unique users found on four Islamic-based web-forums. Several characteristics of each user’s postings were examined, including their posting behavior and the content of their posts. The content was analyzed using parts-of-speech tagging, sentiment analysis, and the SIRA algorithm, which accounted for a user’s percentile score for average sentiment score, volume of negative posts, severity of negative posts, and duration of negative posts. Results suggested that there was not a simple typology that best described the most radical users; however, the method was flexible enough to evaluate several properties of a user’s online activity that could identify the most radical users on the forums.

Authors

• Ryan Scrivens, Simon Fraser University

• Garth Davies, Simon Fraser University

• Richard Frank, Simon Fraser University