Online Library

It is only a matter of time before terrorists begin routinely using Twitter, Instagram, and other services in ongoing operations. We have already seen this in a limited manner from al-Shabaab, which tweets its #JihadDispatches on recent battles. But those delivery mechanisms are unlikely to replace the forums as the main environment for conversation and information distribution among jihadis. Twitter and the like provide a more public platform than a password-protected forum, but one critical utility of forums for jihadis is the ability to have relatively private conversations.

This article seeks to examine, quantitatively and qualitatively, one week of official media releases of the Islamic State (IS). Due to the breadth of IS official media releases, this provides a snapshot upon which to better understand the different styles and messaging streams IS releases on a weekly basis. The article shows that IS produces much more material, and on a broader range of topics, than what gets reported in the mainstream media. Execution videos make up just a fraction of the overall output and are dwarfed by the number of IS productions on military affairs, governance, preaching, moral policing, and other themes. The analysis also shows that IS relies very heavily on visual as opposed to text-based propaganda, and that most of its military activities take place in Iraq, not Syria.

VOX-Pol Blog post.

VOX-Pol blog post

VOX-Pol Blog Post.

In recent years, the increasing propagation of hate speech on social media and the urgent need for effective counter-measures have drawn significant investment from governments, companies, and empirical research. Despite a large number of emerging scientific studies to address the problem, a major limitation of existing work is the lack of comparative evaluations, which makes it difficult to assess the contribution of individual works. This paper introduces a new method based on a deep neural network combining convolutional and gated recurrent networks. We conduct an extensive evaluation of the method against several baselines and state of the art on the largest collection of publicly available Twitter datasets to date, and show that compared to previously reported results on these datasets, our proposed method is able to capture both word sequence and order information in short texts, and it sets new benchmark by outperforming on 6 out of 7 datasets by between 1 and 13% in F1. We also extend the existing dataset collection on this task by creating a new dataset covering different topics.