Abstract

Gang violence is a major problem in the United States accounting for a large fraction of homicides and other violent crime. In this paper, we study the problem of early identification of violent gang members. Our approach relies on modified centrality measures that take into account additional data of the individuals in the social network of co-arrestees which together with other arrest metadata provide a rich set of features for a classification algorithm. We show our approach obtains high precision and recall (0.89 and 0.78 respectively) in the case where the entire network is known and out-performs current approaches used by law-enforcement to the problem in the case where the network is discovered overtime by virtue of new arrests - mimicking real-world law-enforcement operations. Operational issues are also discussed as we are preparing to leverage this method in an operational environment.

Original languageEnglish (US)
Title of host publicationProceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining
PublisherAssociation for Computing Machinery
Pages2079-2088
Number of pages10
Volume2015-August
ISBN (Print)9781450336642
DOIs
StatePublished - Aug 10 2015
Event21st ACM SIGKDD Conference on Knowledge Discovery and Data Mining, KDD 2015 - Sydney, Australia
Duration: Aug 10 2015Aug 13 2015

Other

Other21st ACM SIGKDD Conference on Knowledge Discovery and Data Mining, KDD 2015
CountryAustralia
CitySydney
Period8/10/158/13/15

Fingerprint

Law enforcement
Crime
Metadata
Violence

Keywords

  • Criminology
  • Social network analysis

ASJC Scopus subject areas

  • Software
  • Information Systems

Cite this

Shaabani, E., Aleali, A., Shakarian, P., & Bertetto, J. (2015). Early identification of violent criminal gang members. In Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (Vol. 2015-August, pp. 2079-2088). Association for Computing Machinery. https://doi.org/10.1145/2783258.2788618

Early identification of violent criminal gang members. / Shaabani, Elham; Aleali, Ashkan; Shakarian, Paulo; Bertetto, John.

Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. Vol. 2015-August Association for Computing Machinery, 2015. p. 2079-2088.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Shaabani, E, Aleali, A, Shakarian, P & Bertetto, J 2015, Early identification of violent criminal gang members. in Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. vol. 2015-August, Association for Computing Machinery, pp. 2079-2088, 21st ACM SIGKDD Conference on Knowledge Discovery and Data Mining, KDD 2015, Sydney, Australia, 8/10/15. https://doi.org/10.1145/2783258.2788618
Shaabani E, Aleali A, Shakarian P, Bertetto J. Early identification of violent criminal gang members. In Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. Vol. 2015-August. Association for Computing Machinery. 2015. p. 2079-2088 https://doi.org/10.1145/2783258.2788618
Shaabani, Elham ; Aleali, Ashkan ; Shakarian, Paulo ; Bertetto, John. / Early identification of violent criminal gang members. Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. Vol. 2015-August Association for Computing Machinery, 2015. pp. 2079-2088
@inproceedings{ee6850569ddb49b38c3749742cbb43c1,
title = "Early identification of violent criminal gang members",
abstract = "Gang violence is a major problem in the United States accounting for a large fraction of homicides and other violent crime. In this paper, we study the problem of early identification of violent gang members. Our approach relies on modified centrality measures that take into account additional data of the individuals in the social network of co-arrestees which together with other arrest metadata provide a rich set of features for a classification algorithm. We show our approach obtains high precision and recall (0.89 and 0.78 respectively) in the case where the entire network is known and out-performs current approaches used by law-enforcement to the problem in the case where the network is discovered overtime by virtue of new arrests - mimicking real-world law-enforcement operations. Operational issues are also discussed as we are preparing to leverage this method in an operational environment.",
keywords = "Criminology, Social network analysis",
author = "Elham Shaabani and Ashkan Aleali and Paulo Shakarian and John Bertetto",
year = "2015",
month = "8",
day = "10",
doi = "10.1145/2783258.2788618",
language = "English (US)",
isbn = "9781450336642",
volume = "2015-August",
pages = "2079--2088",
booktitle = "Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining",
publisher = "Association for Computing Machinery",

}

TY - GEN

T1 - Early identification of violent criminal gang members

AU - Shaabani, Elham

AU - Aleali, Ashkan

AU - Shakarian, Paulo

AU - Bertetto, John

PY - 2015/8/10

Y1 - 2015/8/10

N2 - Gang violence is a major problem in the United States accounting for a large fraction of homicides and other violent crime. In this paper, we study the problem of early identification of violent gang members. Our approach relies on modified centrality measures that take into account additional data of the individuals in the social network of co-arrestees which together with other arrest metadata provide a rich set of features for a classification algorithm. We show our approach obtains high precision and recall (0.89 and 0.78 respectively) in the case where the entire network is known and out-performs current approaches used by law-enforcement to the problem in the case where the network is discovered overtime by virtue of new arrests - mimicking real-world law-enforcement operations. Operational issues are also discussed as we are preparing to leverage this method in an operational environment.

AB - Gang violence is a major problem in the United States accounting for a large fraction of homicides and other violent crime. In this paper, we study the problem of early identification of violent gang members. Our approach relies on modified centrality measures that take into account additional data of the individuals in the social network of co-arrestees which together with other arrest metadata provide a rich set of features for a classification algorithm. We show our approach obtains high precision and recall (0.89 and 0.78 respectively) in the case where the entire network is known and out-performs current approaches used by law-enforcement to the problem in the case where the network is discovered overtime by virtue of new arrests - mimicking real-world law-enforcement operations. Operational issues are also discussed as we are preparing to leverage this method in an operational environment.

KW - Criminology

KW - Social network analysis

UR - http://www.scopus.com/inward/record.url?scp=84954161688&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84954161688&partnerID=8YFLogxK

U2 - 10.1145/2783258.2788618

DO - 10.1145/2783258.2788618

M3 - Conference contribution

AN - SCOPUS:84954161688

SN - 9781450336642

VL - 2015-August

SP - 2079

EP - 2088

BT - Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining

PB - Association for Computing Machinery

ER -