Online Library

VOX-Pol Blog post.

In this paper we use methods of social network analysis to examine the inter-organizational structure of the white supremacist movement. Treating links between Internet websites as ties of affinity, communication, or potential coordination, we investigate the structural properties of connections among white supremacist groups. White supremacism appears to be a relatively decentralized movement with multiple centers of influence, but without sharp cleavages between factions. Interorganizational links are stronger among groups with a special interest in mutual affirmation of their intellectual legitimacy (Holocaust revisionists) or cultural identity (racist skinheads) and weaker among groups that compete for members (political parties) or customers (commercial enterprises). The network is relatively isolated from both mainstream conservatives and other extremist groups. Christian Identity theology appears ineffective as a unifying creed of the movement, while Nazi sympathies are pervasive. Recruitment is facilitated by links between youth and adult organizations and by the propaganda efforts of more covertly racist groups. Links connect groups in many countries, suggesting the potential of the Internet to facilitate a whitesupremacist “cyber-community” that transcends regional and national boundaries.

The use of “Big Data” in policy and decision making is a current topic of debate. The 2013 murder of Drummer Lee Rigby in Woolwich, London, UK led to an extensive public reaction on social media, providing the opportunity to study the spread of online hate speech (cyber hate) on Twitter. Human annotated Twitter data was collected in the immediate aftermath of Rigby’s murder to train and test a supervised machine learning text classifier that distinguishes between hateful and/or antagonistic responses with a focus on race, ethnicity, or religion; and more general responses. Classification features were derived from the content of each tweet, including grammatical dependencies between words to recognize “othering” phrases, incitement to respond with antagonistic action, and claims of well-founded or justified discrimination against social groups. The results of the classifier were optimal using a combination of probabilistic, rule-based, and spatial-based classifiers with a voted ensemble meta-classifier. We demonstrate how the results of the classifier can be robustly utilized in a statistical model used to forecast the likely spread of cyber hate in a sample of Twitter data. The applications to policy and decision making are discussed.

Hateful and antagonistic content published and propagated via the World Wide Web has the potential to cause harm and suffering on an individual basis, and lead to social tension and disorder beyond cyber space. Despite new legislation aimed at prosecuting those who misuse new forms of communication to post threatening, harassing, or grossly offensive language – or cyber hate – and the fact large social media companies have committed to protecting their users from harm, it goes largely unpunished due to difficulties in policing online public spaces. To support the automatic detection of cyber hate online, specifically on Twitter, we build multiple individual models to classify cyber hate for a range of protected characteristics including race, disability and sexual orientation. We use text parsing to extract typed dependencies, which represent syntactic and grammatical relationships between words, and are shown to capture ‘othering’ language – consistently improving machine classification for different types of cyber hate beyond the use of a Bag of Words and known hateful terms. Furthermore, we build a data-driven blended model of cyber hate to improve classification where more than one protected characteristic may be attacked (e.g. race and sexual orientation), contributing to the nascent study of intersectionality in hate crime.

Hateful and antagonistic content published and propagated via the World Wide Web has the potential to cause harm and suffering on an individual basis, and lead to social tension and disorder beyond cyber space. Despite new legislation aimed at prosecuting those who misuse new forms of communication to post threatening, harassing, or grossly offensive language – or cyber hate – and the fact large social media companies have committed to protecting their users from harm, it goes largely unpunished due to difficulties in policing online public spaces. To support the automatic detection of cyber hate online, specifically on Twitter, we build multiple individual models to classify cyber hate for a range of protected characteristics including race, disability and sexual orientation. We use text parsing to extract typed dependencies, which represent syntactic and grammatical relationships between words, and are shown to capture ‘othering’ language – consistently improving machine classification for different types of cyber hate beyond the use of a Bag of Words and known hateful terms. Furthermore, we build a data-driven blended model of cyber hate to improve classification where more than one protected characteristic may be attacked (e.g. race and sexual orientation), contributing to the nascent study of intersectionality in hate crime.

Anno Bunnik explores the ramifications of Big Data for countering terrorism, extremism, and radicalisation. With the recent rise of jihadists and other extremists groups in the Middle East and Europe, how do state agencies respond through the use of Big Data? This chapter critically engages with questions such as the extent to which Big Data can inform us about and help prevent radicalisation. It deals with the role of non-governmental organisations and the private sector in this regard. Bunnik makes the argument that whilst it is inevitable that Big Data will take centre stage in counter-terrorism, its potential should also be utilised to better understand radicalisation and extremism.