ExtremeBB: Enabling Large-Scale Research into Extremism, the Manosphere and Their Correlation by Online Forum Data

Abstract

Online extremism is a growing and pernicious problem, and increasingly linked to real-world violence. We introduce a new resource to help research and understand it: ExtremeBB is a structured textual dataset containing nearly 44M posts made by more than 300K registered members on 12 different online extremist forums, enabling both qualitative and quantitative large-scale analyses of historical trends going back two decades. It enables us to trace the evolution of different strands of extremist ideology; to measure levels of toxicity while exploring and developing the tools to do so better; to track the relationships between online subcultures and external political movements such as MAGA (the importance of which was seen in the attack on the US Capitol in January 2021); and to explore links with misogyny and violence, including radicalisation and recruitment. To illustrate a few potential uses, we apply statistical and data-mining techniques to analyse the online extremist landscape in a variety of ways, from posting patterns through topic modelling to toxicity and the membership overlap across different communities. A picture emerges of communities working as support networks, with complex discussions over a wide variety of topics. The discussions of many topics show a level of disagreement which challenges the perception of homogeneity among these groups. These two features of mutual support and a wide range of attitudes lead us to suggest a more nuanced policy approach than simply shutting down these websites. Censorship might remove the support that lonely and troubled individuals are receiving, and fuel paranoid perceptions that the world is against them, though this must be balanced with other benefits of de-platforming. ExtremeBB can help develop a better understanding of these sub-cultures which may lead to more effective interventions; it also opens up the prospect of research to develop better tools to identify hate speech, and to monitor the effectiveness of any interventions that are undertaken.

PostCog: A tool for interdisciplinary research into underground forums at scale

“…POSTCOG is still in its early stages. We will continue to develop and evaluate it with more participants, as well as expanding it to index content in EXTREMEBB -a newly established dataset covering extremist forums [71]. The continued collection of both cybercrime and extremist forum data requires constant maintenance to defeat anti-scraping countermeasures implemented by administrators [68].…”

Beyond Fish and Bicycles: Exploring the Varieties of Online Women’s Ideological Spaces

“…Communities within the Manosphere exhibit disturbingly increased levels of toxicity, hate, and a proclivity for real-world violence [23,26,74]. There is also a connection between them and the alt-right [2,55,92]. The alt-right has embraced the practice of describing women as "shield maidens" and "trad wives," which serves to mask their underlying white supremacist ideology [49].…”

Automated hate speech detection and span extraction in underground hacking and extremist forums

“…The paper describes hate speech annotations for posts extracted from HackForums, an underground forum and Stormfront and Incels.co, two extremist forums. These posts come from the pre-existing CrimeBB and ExtremeBB databases (Pastrana et al 2018a;Vu et al 2021). Based on the sampled data, the paper also analyses the frequency and the content of hate speech across these forums.…”

“…We used existing datasets called CrimeBB (Pastrana et al 2018a) and ExtremeBB (Vu et al 2021) that contain posts from underground and extremist forums, respectively. CrimeBB and ExtremeBB are collected and maintained by the Cambridge Cybercrime Centre.…”