https://doi.org/10.4081/let.2018.680
MACHINE LEARNING PER CARATTERIZZARE GLI ATTACCHI TERRORISTICI
All claims expressed in this article are solely those of the authors and do not necessarily represent those of their affiliated organizations, or those of the publisher, the editors and the reviewers. Any product that may be evaluated in this article or claim that may be made by its manufacturer is not guaranteed or endorsed by the publisher.
Pubblicato: 15 luglio 2020
For security departments understanding the dynamics of terrorist events finding significant and recurrent patterns can have an important impact in the counter-terrorism strategy development. Machine learning techniques coupled with domain knowledge are useful to understand terrorist behaviours with high accuracy, thus helping policy makers for time-sensitive understanding of terrorist activity, which can enable precautions to avoid against future attacks. In this paper different computational techniques, able to derive relationships among terrorist attacks and detect terrorist behaviours, are used on the Global Terrorism Database. The analysis proposed in this paper could help security and government departments to prevent terrorist attacks and to reduce financial, human and political losses. Furthermore, this information can be useful for law enforcement agencies to propose reactive strategies.