Linking Terrorist Network Structure to Lethality: Algorithms and Analysis of Al Qaeda and ISIS

Youdinghuan Chen, Chongyang Gao, Daveed Gartenstein-Ross, Kevin T. Greene, Karin Kalif, Sarit Kraus, Francesco Parisi, Chiara Pulice, Anja Subasic, V. S. Subrahmanian

Research output: Contribution to journalArticlepeer-review

1 Scopus citations

Abstract

Without measures of the lethality of terrorist networks, it is very difficult to assess if capturing or killing a terrorist is effective. We present the predictive lethality analysis of terrorist organization (PLATO) algorithm, which merges machine learning with techniques from graph theory and social network analysis to predict the number of attacks that a terrorist network will carry out based on a network structure alone. We show that PLATO is highly accurate on two novel datasets, which cover Al Qaeda (AQ) and the Islamic State (ISIS). Using both machine learning and statistical methods, we show that the most significant macrofeatures for predicting AQ's lethality are related to their public communications (PCs) and logistical subnetworks, while the leadership and operational subnetworks are most impactful for predicting ISISs lethality. Across both groups, the average degree and the diameters of the strongly connected components (SCCs) within these networks are strongly linked with lethality.

Original languageEnglish
Pages (from-to)2814-2826
Number of pages13
JournalIEEE Transactions on Computational Social Systems
Volume10
Issue number5
DOIs
StatePublished - 1 Oct 2023

Bibliographical note

Publisher Copyright:
© 2014 IEEE.

Funding

This work was supported in part by the Office of Naval Research (ONR) under Grant N00014-16-1-2918.

FundersFunder number
Office of Naval ResearchN00014-16-1-2918

    Keywords

    • Counterterrorism
    • machine learning
    • terrorism

    Fingerprint

    Dive into the research topics of 'Linking Terrorist Network Structure to Lethality: Algorithms and Analysis of Al Qaeda and ISIS'. Together they form a unique fingerprint.

    Cite this