Analyzing a dark web forum page in the context of international security and terrorism: A topic modeling approach

Illegal activities in the Dark Web are the most serious concerns facing governments around the world. Dark Web makes it harder to discover criminals and monitor their activities, since it enables anonymity due to specific technologies such as TOR. As a result, it has turned into a platform for a variety of criminal activities, including pornography, weapon trafficking, drug trafficking, fake documents, and, most notably terrorism as detailed in this thesis. Terrorism in the dark web is a global problem that requires multilateral response at the national, regional, and global levels. This study aims to uncover the topics discussed in Dark Web by using LDA-based topic modeling approach in order to present an overview of terrorists' communication in cyberspace for the detection of unusual behavior or terrorism-related purposes. A Dark Web jihadist forum site which called as Ummah was used as dataset. As a result of the analysis, 30 topics discussed in the forum were revealed. According to the findings, topics obtained from jihadist forum are divided into six categories: "International Conflicts and War", "Terrorism", "Religious Preaching", "Racism and Muslim-related issues", "Propaganda" and "Forum-related issues". These categories are grouped under two main terrorists' dark web usage purposes: recruitment and propaganda. While religious teachings were used as recruitment tool, "conflicts of interest", "wars", "terrorism", "Muslim-related issues and Racism" were used as propaganda tools. There was no direct evidence of terrorist collaboration at the conclusion of the investigation. This does not, however, imply that these sites are risk-free. Propaganda and recruitment tools feed the terrorist activities. In the deeper layers of the Dark Web, recruited members communicate and organize terrorist activities.