Analysing the digital transformation of the market for fake documents using a computational linguistic approach

Abstract

The market for fake documents on the internet is a topic that has not yet been explored in depth, despite its importance in facilitating many crimes. This research explored the market of fake documents on the White House Market anonymous market with a computational linguistic methodology; more specifically using textometry. The textual corpus is composed of the data of the ads titles as well as the profiles of the sellers, which were analysed as traces of their online activities. We investigated how these remnants can help to answer general questions. What kinds of fake documents are sold? Can we distinguish types of sellers based on their selling activities or profiles? Can we link distinct vendors based on language trace similarities? The free software IRaMuTeQ was used to carry out the analysis. The results showed that the textometric methods have real potential in classification, highlighting the different products on the market, and grouping the sellers according to their offers.

Keywords

• Fake documents
• Cryptomarket
• Computational linguistic
• Textometry
• Language trace