Online Library

This article offers a method for systematically grading the quality of Islamic State of Iraq and Syria (ISIS) videos based on technical production criteria. Using this method revealed moments when ISIS production capacity was severely debilitated (Fall 2015) and when they began to rebuild (Spring 2016), which the article details. Uses for
this method include evaluating propaganda video output across time and across groups, and the ability to assess kinetic actions against propaganda organizations. This capacity will be critical as Islamic State media production teams will be pushed out of its territory as the State collapses.

From a technical standpoint, Islamic State (IS) videos are demonstrably superior to those of other groups. But as time goes by, their aesthetic is migrating downstream as other groups attempt to copy it. Specifically, IS has turned to video games, regularly mimicking and even directly copying the aesthetic and design of First Person Shooter games, most often Call of Duty, in their videos, and other groups have followed suit. This specific aesthetic offers a way to recruit young, technologically savvy, men while sanitizing the violence they were being recruited to participate in. This study offers an instrument for tracking the IS aesthetic as it moves to other groups as well as its evolution over time, and offers a case study of a specific group that has copied the IS aesthetic, Hay’at Tahrir al-Sham (HTS.)

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.

The increasing presence of hate speech on social media has drawn significant investment from governments, companies, and empirical research. Existing methods typically use a supervised text classification approach that depends on carefully engineered features. However, it is unclear if these features contribute equally to the performance of such methods. We conduct a feature selection analysis in such a task using Twitter as a case study, and show findings that challenge conventional perception of the importance of manual feature engineering: automatic feature selection can drastically reduce the carefully engineered features by over 90% and selects predominantly generic features often used by many other language related tasks; nevertheless, the resulting models perform better using automatically selected features than carefully crafted task-specific features.

VOX-Pol Blog post.

VOX-Pol Blog Post.