Machine Learning for Affect Analysis on White Supremacy Forum

Abstract: Since the inception of the World Wide Web, security agencies, researchers, and analysts have focused much of their attention on the sentiment found on hate-inspired webforums. Here, one of their goals has been to detect and measure users' affects that are expressed in the forums as well as identify how users' affects change over time. Manual inspection has been one way to do this; however, as the number of discussion posts and sub-forums increase, there has been a growing need for an automated system that can assist humans in their analysis. The aim of this thesis, then, is to detect and measure a number of affects expressed in written text on Stormfront.org, the most visited hate forum on the Web. To do this, we used a machine learning approach where we trained a model to recognize affects on three sub-forums: Ideology and Philosophy, For Stormfront Ladies Only, and Stormfront Ireland. The training data consisted of manually annotated data and the affects we focused on were racism, aggression, and worries. Results indicate that even though measuring affects is a subjective process, machine learning is a promising way forward to  analyse and measure the presence of different affects on hate forums.