Machine Learning Methods for Detecting and Monitoring Extremist Information on the Internet

摘要

In this paper, we employ machine learning methods to solve the problem of countering terrorism and extremism by using information from the Internet. This problem involves retrieving electronic messages, documents, and web resources that potentially contain information of terrorist or extremist nature, identifying the structure of user groups and online communities that disseminate this information, monitoring and modeling information flows in these communities, as well as assessing threats and predicting risks based on monitoring results. We propose some original language-independent algorithms for pattern-based information retrieval, thematic modeling, and prediction of message flow characteristics, as well as assessment and prediction of potential risk coming from members of online communities by using data on the structure of relations in these communities, which makes it possible to detect potentially dangerous users even without full access to the content they distribute, e.g., through private channels and chat rooms.