Online Library

The permanent transition to online activity has brought with it a surge in hate speech discourse. This has prompted increased calls for automatic detection methods, most of which currently rely on a dictionary of hate speech words, and supervised classification. This approach often falls short when dealing with newer words and phrases produced by online extremist communities. These code words are used with the aim of evading automatic detection by systems. Code words are frequently used and have benign meanings in regular discourse, for instance, “skypes, googles, bing, yahoos” are all examples of words that have a hidden hate speech meaning. Such overlap presents a challenge to the traditional keyword approach of collecting data that is specific to hate speech. In this work, we first introduced a word embedding model that learns the hidden hate speech meaning of words. With this insight on code words, we developed a classifier that leverages linguistic patterns to reduce the impact of individual words. The proposed method was evaluated across three different datasets to test its generalizability. The empirical results show that the linguistic patterns approach outperforms the baselines and enables further analysis on hate speech expressions.

Without measures of the lethality of terrorist networks, it is very difficult to assess if capturing or killing a terrorist is effective. We present the predictive lethality analysis of terrorist organization () algorithm, which merges machine learning with techniques from graph theory and social network analysis to predict the number of attacks that a terrorist network will carry out based on a network structure alone. We show that is highly accurate on two novel datasets, which cover Al Qaeda (AQ) and the Islamic State (ISIS). Using both machine learning and statistical methods, we show that the most significant macrofeatures for predicting AQ’s lethality are related to their public communications (PCs) and logistical subnetworks, while the leadership and operational subnetworks are most impactful for predicting ISISs lethality. Across both groups, the average degree and the diameters of the strongly connected components (SCCs) within these networks are strongly linked with lethality.

Linksextreme Medien wollen nicht möglichst objektiv über allgemeine Belange berichten. Sie sind auch keine Wirtschaftsunternehmen, die kundenorientiert Leistungen verkaufen wollen. Sie verfolgen politische Ziele – und bekämpfen die politischen Gegner.

This article aims to map the online propaganda presence and activities of the Turkestan Islamic Party’s media arm—Islam Awazi (“Voice of Islam”). It also discusses its capabilities in terms of producing new releases and attracting online audiences. In order to reach these objectives, this study exploited a methodology which is a combination of open source intelligence techniques (OSINT) with limited content analysis. It argues that the Uyghur-oriented Islam Awazi’s (IA) propaganda strategy was primarily based on one standalone website, which constituted a central repository of its new productions. It was supported by several Telegram channels. However, open source intelligence investigation allowed other domains proliferating the IA’s productions, which were still accessible but abandoned at the time when this study was carried out, to be discovered. It also proved that the organization was capable of producing more than 160 propaganda releases between January and September 2020. Their viewership on the surface web was, however, quite limited. Finally, this study also outlines a peculiar connection between Islam Awazi’s websites and two networks of domains exploited by the cyber-criminal underground to distribute pornography and malware. This may be considered as a sign of an existing—and widely discussed by the academia—terror-crime nexus.

This literature review seeks to reorient the discourse on radicalization to consider the connection between communication technology and violent extremism. By interrogating three central questions vexing policy-makers, law enforcement officials and academics, this review moves away from a monolithic understanding of the internet and showcases the opportunities afforded by different communications technologies within the context of radicalization and recruitment. As this discussion shows, there is a consensus that despite significant exceptions to the rule, the internet alone does not act as a radicalizing agent, but rather serves as a facilitator and catalyst for terrorist organizations and their respective networks. Despite varying analyses produced within the literature, there is agreement that the virtual sphere does not replace the real world in most instances. Above all, a review of the current literature demonstrates that to answer the crucial questions posed in this article, more empirically-based research is required. This article is a revised and updated version of the 2017 VOX-Pol report Research Perspectives on Online Radicalisation: A Literature Review 2006 to 2016.

With the exponential development of the virtual environment and social networks, radical elements have managed to promote and disseminate their radical ideas, in less time, to a wider and more diversified audience than in the past. This aspect has caused a shift of radicalization processes from the offline environment to the online environment, turning online radicalization into one of the biggest security challenges. This paper aims to (1) provide an insight into the hypothesis according to which the live-streaming of terrorist attacks in recent years could become a new radicalization mechanism, perhaps generating a new trend and (2) identify the elements and dynamics that determine attackers to use live-stream platforms at the time of the terrorist attack. The article proposes an analysis of the current theoretical framework that combines the brief analysis of the main models of online radicalization, highlighting the elements that could underlie a new radicalization model focused on live-stream/copycat terrorist attacks. In this article we aim to answer the following research question: can live-streaming represent a new mechanism of radicalization?