Terrorists and extremists use the Internet to recruit new members, spread propaganda, and plan attacks. The size and scope of these dark corners of the Web are vast and disturbing. A team of computational scientists at the Artificial Intelligence Lab at the University of Arizona is using new approaches to track terrorists' moves online. Funded by the National Science Foundation and other federal agencies, the team has created the Dark Web Project to collect and analyze all terrorist-generated content on the Web.
Using techniques such as Web spidering, link analysis, content analysis, authorship analysis, sentiment analysis, and multimedia analysis, the team can find, catalogue, and analyze extremist activities online. One of the tools developed by Dark Web is a technique called Writeprint, which automatically extracts thousands of multilingual, structural, and semantic features to determine who is creating anonymous content online. Writeprint can determine with more than 95 percent accuracy if the author has produced other content in the past. The system alerts analysts when the same author produces new content.
Dark Web's capabilities are also being used to study the online presence of extremist groups and other social movement organizations. The team sees other applications for this Web mining approach for other academic fields, and to study societal change.