Solutions to Detect and Analyze Online Radicalization : A Survey

TL;DR

This survey reviews 40 research papers on detecting online radicalization, analyzing various techniques, trends, limitations, and identifying gaps in the field from 2003 to 2011.

Contribution

It introduces a novel classification scheme for existing solutions and provides a comprehensive analysis of research trends and gaps in online radicalization detection methods.

Findings

Various platforms are exploited for radicalization and hate speech.

Existing techniques face challenges due to data volume and content noise.

Research gaps include real-time detection and adaptive algorithms.

Abstract

Online Radicalization (also called Cyber-Terrorism or Extremism or Cyber-Racism or Cyber- Hate) is widespread and has become a major and growing concern to the society, governments and law enforcement agencies around the world. Research shows that various platforms on the Internet (low barrier to publish content, allows anonymity, provides exposure to millions of users and a potential of a very quick and widespread diffusion of message) such as YouTube (a popular video sharing website), Twitter (an online micro-blogging service), Facebook (a popular social networking website), online discussion forums and blogosphere are being misused for malicious intent. Such platforms are being used to form hate groups, racist communities, spread extremist agenda, incite anger or violence, promote radicalization, recruit members and create virtual organi- zations and communities. Automatic detection of online radicalization is a technically challenging problem because of the vast amount of the data, unstructured and noisy user-generated content, dynamically changing content and adversary behavior. There are several solutions proposed in the literature aiming to combat and counter cyber-hate and cyber-extremism. In this survey, we review solutions to detect and analyze online radicalization. We review 40 papers published at 12 venues from June 2003 to November 2011. We present a novel classification scheme to classify these papers. We analyze these techniques, perform trend analysis, discuss limitations of existing techniques and find out research gaps.