Learning future terrorist targets through temporal meta-graphs

Abstract In the last 20 years, terrorism has led to hundreds of thousands of deaths and massive economic, political, and humanitarian crises in several regions of the world. Using real-world data on attacks occurred in Afghanistan and Iraq from 2001 to 2018, we propose the use of temporal meta-graph...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Gian Maria Campedelli, Mihovil Bartulovic, Kathleen M. Carley
Formato:	article
Lenguaje:	EN
Publicado:	Nature Portfolio 2021
Materias:	Medicine R Science Q
Acceso en línea:	https://doaj.org/article/990abd3a107c41f394935ac5d9d90f7a
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:990abd3a107c41f394935ac5d9d90f7a
record_format	dspace
spelling	oai:doaj.org-article:990abd3a107c41f394935ac5d9d90f7a2021-12-02T17:32:57ZLearning future terrorist targets through temporal meta-graphs10.1038/s41598-021-87709-72045-2322https://doaj.org/article/990abd3a107c41f394935ac5d9d90f7a2021-04-01T00:00:00Zhttps://doi.org/10.1038/s41598-021-87709-7https://doaj.org/toc/2045-2322Abstract In the last 20 years, terrorism has led to hundreds of thousands of deaths and massive economic, political, and humanitarian crises in several regions of the world. Using real-world data on attacks occurred in Afghanistan and Iraq from 2001 to 2018, we propose the use of temporal meta-graphs and deep learning to forecast future terrorist targets. Focusing on three event dimensions, i.e., employed weapons, deployed tactics and chosen targets, meta-graphs map the connections among temporally close attacks, capturing their operational similarities and dependencies. From these temporal meta-graphs, we derive 2-day-based time series that measure the centrality of each feature within each dimension over time. Formulating the problem in the context of the strategic behavior of terrorist actors, these multivariate temporal sequences are then utilized to learn what target types are at the highest risk of being chosen. The paper makes two contributions. First, it demonstrates that engineering the feature space via temporal meta-graphs produces richer knowledge than shallow time-series that only rely on frequency of feature occurrences. Second, the performed experiments reveal that bi-directional LSTM networks achieve superior forecasting performance compared to other algorithms, calling for future research aiming at fully discovering the potential of artificial intelligence to counter terrorist violence.Gian Maria CampedelliMihovil BartulovicKathleen M. CarleyNature PortfolioarticleMedicineRScienceQENScientific Reports, Vol 11, Iss 1, Pp 1-15 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Medicine R Science Q
spellingShingle	Medicine R Science Q Gian Maria Campedelli Mihovil Bartulovic Kathleen M. Carley Learning future terrorist targets through temporal meta-graphs
description	Abstract In the last 20 years, terrorism has led to hundreds of thousands of deaths and massive economic, political, and humanitarian crises in several regions of the world. Using real-world data on attacks occurred in Afghanistan and Iraq from 2001 to 2018, we propose the use of temporal meta-graphs and deep learning to forecast future terrorist targets. Focusing on three event dimensions, i.e., employed weapons, deployed tactics and chosen targets, meta-graphs map the connections among temporally close attacks, capturing their operational similarities and dependencies. From these temporal meta-graphs, we derive 2-day-based time series that measure the centrality of each feature within each dimension over time. Formulating the problem in the context of the strategic behavior of terrorist actors, these multivariate temporal sequences are then utilized to learn what target types are at the highest risk of being chosen. The paper makes two contributions. First, it demonstrates that engineering the feature space via temporal meta-graphs produces richer knowledge than shallow time-series that only rely on frequency of feature occurrences. Second, the performed experiments reveal that bi-directional LSTM networks achieve superior forecasting performance compared to other algorithms, calling for future research aiming at fully discovering the potential of artificial intelligence to counter terrorist violence.
format	article
author	Gian Maria Campedelli Mihovil Bartulovic Kathleen M. Carley
author_facet	Gian Maria Campedelli Mihovil Bartulovic Kathleen M. Carley
author_sort	Gian Maria Campedelli
title	Learning future terrorist targets through temporal meta-graphs
title_short	Learning future terrorist targets through temporal meta-graphs
title_full	Learning future terrorist targets through temporal meta-graphs
title_fullStr	Learning future terrorist targets through temporal meta-graphs
title_full_unstemmed	Learning future terrorist targets through temporal meta-graphs
title_sort	learning future terrorist targets through temporal meta-graphs
publisher	Nature Portfolio
publishDate	2021
url	https://doaj.org/article/990abd3a107c41f394935ac5d9d90f7a
work_keys_str_mv	AT gianmariacampedelli learningfutureterroristtargetsthroughtemporalmetagraphs AT mihovilbartulovic learningfutureterroristtargetsthroughtemporalmetagraphs AT kathleenmcarley learningfutureterroristtargetsthroughtemporalmetagraphs
_version_	1718380137087500288

Learning future terrorist targets through temporal meta-graphs

Ejemplares similares