Online Library

Community Action for Preventing Extremism (CAPE) is Australia’s only not-for-profit counter-extremism project focused specifically on preventing a growth in right-wing extremism. By disseminating counter-narratives to extremism through the exitwhitepower.com website and directly engaging with individuals at-risk via social media, CAPE seeks to sow a seed of doubt that will reduce individual’s vulnerability to involvement in the far-right. This paper will outline CAPE’s practitioner experience in developing online interventions to challenge far-right narratives and the advantages of using this method of engagement. The paper will also outline distinctions between traditional white supremacist far-right groups and the increasingly active anti-Muslim groups, which create challenges for CAPE’s work in countering far-right online activity.

We have collected over 30M messages from the publicly available /pol/ message boards on 4chan and 8chan, and compiled them into a model of toxic language use. The trained word embeddings (±0.4GB) are released for free and may be useful for further study on toxic discourse or to boost hate speech detection systems: textgain.com/8chan.

VOX-Pol: An Introduction

The increasing use of online social networks (OSNs) by extremists for the spread of radicalization have been a great concern for law enforcement agencies across the world. Today, they are being increasingly used by radical groups for spreading ideologies, recruitment, influencing and planning their activities. However, many of such groups remain hidden within the social fabric and can only be discovered by analyzing the related content posted by them. This article addresses the missing line of research by analyzing hidden online Radical networks along three dimensions—element level, group-level, and network level and addresses the gap which the present metrics for social network analysis fail to address as we graduate toward the dynamic network analysis. We propose new metrics to analyze the evolving topic-centric network and present our findings about the understanding of properties of such complex networks in the information network of Twitter with the existing as well the new proposed metrics.

The growing penetration of online social networks (OSNs) has emerged as a strong operational tool for spreading online radicalization by adding intensity and acceleration to the operations of radical groups. The efficiency of ways and methods proposed to measure the dynamics of radicalization are limited by the availability of models for modeling the intricacies of human dynamics and heterogeneous time varying interactions. Most of the developed algorithms and tools mainly focus on the static network structures and tend to ignore the “origin” of a new radical idea or propagation of a “weak” topic which might find its relevance in the security domain later on with the passage of time. In this article we propose a mathematical model for measuring dynamic propagation of radicalization in OSNs using Discrete Time Markov Chains by discretizing the continuous time domain. We also discuss our experimental results obtained through the information network of Twitter. The approach presented here is scalable and can easily be extended for modeling diffusion of general topics in OSNs.