Collection of U.S. extremist online forums: A web mining approach

Extremists' exploitation of computer-mediated communications such as online forums has recently gained much attention from academia and the government. However, due to the covert nature of these forums and the dynamic nature of the Internet, there have been no systematic methodologies developed for collection and analysis of online information created by extremists. In this study, we propose a systematic Web mining approach to collecting and monitoring extremist forums. Our proposed approach identifies extremist forums from various resources, addresses practical issues faced by researchers and experts in the extremist forum collection process. Such collection provides a foundation for quantitative forum analysis. Using the proposed approach, we created a collection of 110 U.S. domestic extremist forums containing more than 640,000 documents. We also report our findings on the multimedia usage pattern, participant distribution, and posting activity distribution. The collection building results demonstrate the effectiveness and feasibility of our approach. Furthermore, the extremist forum collection we created could serve as an invaluable data source to enable a better understanding of the extremists' movements.