The Extreme Right Filter Bubble

Abstract: Due to its status as the most popular video sharing platform, YouTube plays an important role in the online strategy of extreme right groups, where it is often used to host associated content such as music and other propaganda. In this paper, we develop a categorization suitable for the analysis of extreme right channels found on YouTube. By combining this with an NMF-based topic modelling method, we categorize channels originating from links propagated by extreme right Twitter accounts. This method is also used to categorize related channels, which are determined using results returned by YouTube's related video service. We identify the existence of a "filter bubble", whereby users who access an extreme right YouTube video are highly likely to be recommended further extreme right content.