Online Library

We present a machine learning framework that leverages a mixture of metadata, network, and temporal features to detect extremist users, and predict content adopters and interaction reciprocity in social media. We exploit a unique dataset containing millions of tweets generated by more than 25 thousand users who have been manually identified, reported, and suspended by Twitter due to their involvement with extremist campaigns. We also leverage millions of tweets generated by a random sample of 25 thousand regular users who were exposed to, or consumed, extremist content. We carry out three forecasting tasks, (i) to detect extremist users, (ii) to estimate whether regular users will adopt extremist content, and finally (iii) to predict whether users will reciprocate contacts initiated by extremists. All forecasting tasks are set up in two scenarios: a post hoc (time independent) prediction task on aggregated data, and a simulated real-time prediction task. The performance of our framework is extremely promising, yielding in the different forecasting scenarios up to 93% AUC for extremist user detection, up to 80% AUC for content adoption prediction, and finally up to 72% AUC for interaction reciprocity forecasting. We conclude by providing a thorough feature analysis that helps determine which are the emerging signals that provide predictive power in different scenarios.

Recent terrorist attacks carried out on behalf of ISIS on American and European soil by lone wolf attackers or sleeper cells remind us of the importance of understanding the dynamics of radicalization mediated by social media communication channels. In this paper, we shed light on the social media activity of a group of twenty-five thousand users whose association with ISIS online radical propaganda has been manually verified. By using a computational tool known as dynamical activity-connectivity maps, based on network and temporal activity patterns, we investigate the dynamics of social influence within ISIS supporters. We finally quantify the effectiveness of ISIS propaganda by determining the adoption of extremist content in the general population and draw a parallel between radical propaganda and epidemics spreading, highlighting that information broadcasters and influential ISIS supporters generate highly-infectious cascades of information contagion. Our findings will help generate effective countermeasures to combat the group and other forms of online extremism.

Recent terrorist attacks carried out on behalf of ISIS on American and European soil by lone wolf attackers or sleeper cells remind us of the importance of understanding the dynamics of radicalization mediated by social media communication channels. In this paper, we shed light on the social media activity of a group of twenty-five thousand users whose association with ISIS online radical propaganda has been manually verified. By using a computational tool known as dynamic activity-connectivity maps, based on network and temporal activity patterns, we investigate the dynamics of social influence within ISIS supporters. We finally quantify the effectiveness of ISIS propaganda by determining the adoption of extremist content in the general population and draw a parallel between radical propaganda and epidemics spreading, highlighting that information broadcasters and influential ISIS supporters generate highly-infectious cascades of information contagion. Our findings will help generate effective countermeasures to combat the group and other forms of online extremism.

We present a machine learning framework that leverages a mixture of metadata, network, and temporal features to detect extremist users, and predict content adopters and interaction reciprocity in social media. We exploit a unique dataset containing millions of tweets generated by more than 25 thousand users who have been manually identified, reported, and suspended by Twitter due to their involvement with extremist campaigns. We also leverage millions of tweets generated by a random sample of 25 thousand regular users who were exposed to, or consumed, extremist content. We carry out three forecasting tasks, (i) to detect extremist users, (ii) to estimate whether regular users will adopt extremist content, and finally (iii) to predict whether users will reciprocate contacts initiated by extremists. All forecasting tasks are set up in two scenarios: a post hoc (time independent) prediction task on aggregated data, and a simulated real-time prediction task. The performance of our framework is extremely promising, yielding in the different forecasting scenarios up to 93 % AUC for extremist user detection, up to 80 % AUC for content adoption prediction, and finally up to 72 % AUC for interaction reciprocity forecasting. We conclude by providing a thorough feature analysis that helps determine which are the emerging signals that provide predictive power in different scenarios.

As white nationalists have come to increasing prominence in recent decades, their presence presents a significant challenge to democratic societies. Motivated by a sense of racial imperilment, and opposed, sometimes violently, to core democratic ideals, white nationalists cannot be meaningfully incorporated into the political life of societies which promote inclusiveness and pluralism without threatening those values. Yet democratic theory, which seeks to offer ideal visions of what democratic societies could look like, provides no means for contending with the active presence of white nationalism in contemporary democratic societies. This article uses the concept of voice to explore these shortcomings in several theories of democracy, including deliberative, agonistic, and empowerment theories. In doing so, it draws on a wealth of white nationalist media, both physical and digital, to demonstrate how attitudes regarding racial imperilment, often articulated in terms of a ‘white genocide’, foreclose on any possibility of incorporating white nationalist voices into democratic societies. Moreover, an examination of white nationalists’ ongoing project to shift the boundaries of what is permissible in popular discourse, a process which is amplified by digital media technologies, suggests that they are nevertheless a pressing problem for democratic societies which should be addressed. In doing so, it is important to move beyond the focus on voice which underlays much democratic theory, exploring instead the experiences of social life to which white nationalist voices speak so that we might gain a better understanding of what motivates white nationalist voice and, potentially, how it might be addressed.

Governments have long worried about terrorists using the Internet to launch cyberattacks, spread propaganda, recruit and radicalise individuals and raise funds. However, the Islamic State’s exploitation of social media has caused a crisis and generated questions about international law’s role in addressing terrorism in cyberspace. This article analyzes international law in connection with potential terrorist cyberattacks and terrorist use of cyber technologies for other purposes. International law is not well positioned to support responses to terrorist cyberattacks, but the lack of such attacks to date undermines incentives for states to develop international law against this threat. In terms of terrorists using the Internet and social media for propaganda, radicalisation, recruiting and fundraising, the crisis caused by the Islamic State’s online activities has not created consensus strong enough to support a prominent role for international law in countering cyber-facilitated terrorism.