Mining Pro-ISIS Radicalisation Signals from Social Media Users

25 February 2020

Details

Authors: Matthew Rowe & Hassan Saif

Date of Publication: 2016

Journal / Publisher: Proceedings of the Tenth International AAAI Conference on Web and Social Media

Purpose of the study

Key questions

How can we detect when a user has adopted a pro-ISIS stance (i.e. is exhibiting radicalised behaviour on social media)?

What happens to Twitter users before they exhibit radicalized behaviour, and also after such exhibition?

What influences users to adopt pro-ISIS language?

Design

Approach

Collect and study language in posts by Pro-ISIS, Anti-ISIS and Neutral content.

Number of participants

157,000 (users and followers in Europe)

Where

Europe

Type of ‘participant’

Online users who create or share violent extremist content

Topic

Both mobilisation to fight abroad and mobilisation to conduct attacks on home soil.

Key findings

Using content based and sharing behavior features, it is possible to identify “activation” points of social media users.

Key recommendations

Identify if “activation” is associated with offline behaviors.

NATO

In 2017, a NATO Research Task Group (HFM-278 RTG) was formed. The RTG, led and Chaired by the UK (Defence Science and Technology Laboratory - Dstl), comprised representatives from 8 countries and various backgrounds (government, academia, police and the intelligence communities). RTG members collaborated to design and develop an ‘Information Repository’ of evidence (literature, data, tools) on violent extremism. The goal was to design a ‘one stop shop’ to enable different end users (including policy makers, frontline CT practitioners, researchers) to quickly and easily access high quality (empirical, scientific, evidence-based) materials to help them to understand specific topic areas and to inform their work: This is the VERE (Violent Extremism Research and Evidence) repository.

VERE is unique in that each document is accompanied by a short overview, written to help the reader understand whether and how the information can be applied in practice. (Some parts of certain overviews include text directly quoting parts of the article that the overview author perceived as important to highlight.) For example, an overview might highlight factors such as the methodological approach taken by researchers, participant demographics and sample size, so that the reader can decide how appropriate it is to apply findings to their own work. In 2020 VERE was taken on by the Centre for Research and Evidence on Security Threats (CREST) and thus amalgamated with the existing Radicalisation Research repository. This repository, alongside the wider Radicalisation Research repository, will be updated regularly to reflect the most up to date literature relating to violent extremism.

2016

External link to article

Conference Paper

Matthew Rowe Hassan Saif

You might also like:

Negative Stereotypical Portrayals of Muslims in Right-Wing Populist Campaigns: Perceived Discrimination, Social Identity Threats, and Hostility Among Young Muslim Adults

20 September 2017

Terrorism, the Internet and the Social Media Advantage: Exploring how terrorist organizations exploit aspects of the internet, social media and how these same platforms could be used to counter-violent extremism

9 January 2020

Promoting Extreme Violence: Visual and Narrative Analysis of Select Ultraviolent Terror Propaganda Videos Produced by the Islamic State of Iraq and Syria (ISIS) in 2015 and 2016

20 February 2019

Promoting Extreme Violence: Visual and Narrative Analysis of Select Ultraviolent Terror Propaganda Videos Produced by the Islamic State of Iraq and Syria (ISIS) in 2015 and 2016

9 November 2018