Using machine learning to identify jihadist messages on Twitter

Abstract: Jihadist groups like ISIS are spreading online propaganda using various forms of social media such as Twitter and YouTube. One of the most common approaches to stop these groups is to suspend accounts that spread propaganda when they are discovered. However, this approach requires that human analysts manually read and analyze an enormous amount of information on social media. In this work we make a first attempt to automatically detect radical content that is released by jihadist groups on Twitter. We use a machine learning approach that classifies a tweet as radical or non-radical and our results indicate that an automated approach to aid analysts in their work with detecting radical content on social media is a promising way forward.