Online Library

Identifying and profiling threat actors are high priority tasks for a number of governmental organizations. These threat actors may operate actively, using the Internet to promote propaganda, recruit new members, or exert command and control over their networks. Alternatively, threat actors may operate passively, demonstrating operational security awareness online while using their Internet presence to gather information they need to pose an offline physical threat. This paper presents a flexible new prototype system that allows analysts to automatically detect, monitor and characterize threat actors and their networks using publicly available information. The proposed prototype system fills a need in the intelligence community for a capability to automate manual construction and analysis of online threat networks. Leveraging graph sampling approaches, we perform targeted data collection of extremist social media accounts and their networks. We design and incorporate new algorithms for role classification and radicalization detection using insights from social science literature of extremism. Additionally, we develop and implement analytics to facilitate monitoring the dynamic social networks over time. The prototype also incorporates several novel machine learning algorithms for threat actor discovery and characterization, such as classification of user posts into discourse categories, user post summaries and gender prediction.

The concept of creating counter-narratives in order to push back against extremist recruitment and propaganda has become well established in recent years. In practice, however, it has proven difficult to curate this content in a systematic way, target it toward at risk audiences, and – most importantly – measure constructive impact on their behaviour. Over the past few years, the Institute for Strategic Dialogue (ISD) has developed research and pilot studies conducted with the Against Violent Extremism (AVE) network of former extremists and survivors of extremism that it manages. This research has been conducted in order to test and improve methodologies that help optimise the impact of counternarrative campaigns. This report outlines the key findings and results of three counter-narrative campaign pilot projects curated through the AVE network in coordination with Jigsaw and with additional in-kind assistance or financial support from Facebook and Twitter. Although some details and figures have been omitted for security purposes, the results of the study are presented in full.

Certain studies of social conflicts and geopolitical processes through online social networks entail qualitative analysis. One such issue is the tension between Western and Muslim societies. We introduce computer-assisted qualitative sentiment analysis for the inquiry and extraction of varied sentiments. The analysis explores the prevalent meanings of the term jihad through discussions of Muslims and non-Muslims in the online public sphere. After examining 4,630 Facebook comments and replies, our examination leads to a holistic mapping that details “peaceful,” “moderate,” and “radical” opinions regarding jihad, which is an integral institution of the Muslim world. Through this method, we suggest a “Muslim–non-Muslim tension indicator,” which can be used in a range of political analyses.

Social media systems allow Internet users a congenial platform to freely express their thoughts and opinions. Although this property represents incredible and unique communication opportunities, it also brings along important challenges. Online hate speech is an archetypal example of such challenges. Despite its magnitude and scale, there is a significant gap in understanding the nature of hate speech on social media. In this paper, we provide the first of a kind systematic large scale measurement study of the main targets of hate speech in online social media. To do that, we gather traces from two social media systems: Whisper and Twitter. We then develop and validate a methodology to identify hate speech on both these systems. Our results identify online hate speech forms and offer a broader understanding of the phenomenon, providing directions for prevention and detection approaches.

This paper summarizes discussions held on 24 May 2016 in Riga, Latvia, which focused on exploring the Kremlin and DAESH information activities in order to improve our understanding of the nature of these communications and their effect on Western societies. The questions discussed were:

How are the communications and messages of DAESH and the Kremlin constructed and disseminated?

Are their methods changing?

Why do such messages appeal to youth, even if they are familiar with Western Values and consumerism?

What are the weakest aspects of our information environment and what can we do to improve?

Social media are useful facilitators when recruiting hidden populations for research. In our research on youth and radicalization, we were able to find and contact young people with extreme ideals through Facebook. In this article, we discuss our experiences using Facebook as a tool for finding respondents who do not trust researchers. Facebook helped us recruit youths with extreme Islamic and extreme left-wing ideals. We conclude by discussing the benefits and limitations of using Facebook when searching for and approaching populations who are difficult to reach.