Towards AI-Driven Prediction of Terrorism Risk Based on the Analysis of Localized Web News

Abstract

This work presents a framework for predicting the likelihood of terrorist incidents within a specific time period in a target country based on machine learning and deep learning models. These models are trained on news data for the target country sourced from the Global Database of Events, Language, and Tone (GDELT), while the terrorist incidents recorded in the Global Terrorist Database (GTD) serve as the ground-truth. To cope with the massive volume of such localised news and the features extracted from them, a novel feature selection process based on Random Forest models is proposed, where the predictive power of each feature is calculated and only features estimated to have sufficient predictive power are subsequently considered. Experiments are performed by considering the United Kingdom as a case study and six predictive models are evaluated across four evaluation metrics. The experimental evaluation results indicate that the proposed framework enhances the predictive power of both machine learning and deep learning models that use the proposed feature selection in forecasting the likelihood of terrorist incidents, surpassing models trained 1) on all baseline features and 2) on features selected by two well established feature selection approaches. Overall, the proposed framework aims at assisting counter-terrorism efforts by providing a projection of the likelihood of terrorist incidents and thus the overall terrorism risk in a target country, using the most valuable features provided by GDELT.

Keywords

• Terrorist incidents
• predictive models
• deep learning
• machine learning
• feature selection
• global terrorism database (GTD)