Text mining on the darknet: use cases in law enforcement studies

Abstract

Aim: The users of cyberspace create an enormous amount of textual data on the surface web and on the deep web as well, including the anonymity based darknet platforms. The various automated analytical methods of text mining allow us to analyse these big data sources, which opportunity is already exploited by several researchers. The aim of my study was to review the use cases which are relevant from the aspect law enforcement studies.
Methodology: As text mining is relatively new in social sciences, I applied state-of-the-art review methodology, which is specialized in reviewing current literature to offer new perspectives in a field of research.
Findings: In the international literature, we can find examples for classifying legal and illegal content by statistical language models, strengthening the theory of darknet’s dual-usage. Darknet markets usually end up being closed by law enforcement agencies, just like it happened in the case of the Silk Road market, back in 2013. Analysing the trends of user activity after the closure of specific darknet markets can help in evaluating the interventions of law enforcement.
Value: By presenting these examples, this study shed light on the exploitable opportunities of text mining as a research method in law enforcement studies.