Abstract
Criminal organizations have been continuously evolving toward more global and structured organizations. This evolution is kindled by emerging communications technologies and open circulation of goods and persons. Fighting efficiently against this new kind of criminal requires a good acknowledgement of spatiotemporal trends. To capture such trends, police records can be used to derive relevant indicators. Yet using such records only would lead us to focus on some specific and well-covered areas. Hence, additional global and local indicators have to be extracted from complementary sources, e.g., open data for low frequency indicators or social media for higher frequency indicators revealing ongoing criminal activity. In this chapter, we focus on social media. Our main contribution lies in the formalization of a generic intelligence-driven process for extracting indicators from social media . We furthermore describe a concrete implementation of this process through the OsintLab platform and illustrate its interest and strength on two experiments. The first one studies copper theft activities, such as relating to the stealing of railway signaling cabling and its subsequent onwards trade, which are closely related to organized crime. The second one aims at understanding the drivers of jihadist propaganda on social media, such as relating to the current threat of Islamic State (IS/ISIS/ISIL/Daesh). Based on our experimental findings, we eventually propose a generic framework for the construction of crime indicators from social media feeds.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
- 2.
- 3.
- 4.
As a comparison measure, keep in mind that popular graphical frameworks like d3.js can hardly display a graph with 1000 nodes….
- 5.
- 6.
This information could be extracted from Twitter metadata when present or extracted from text content with named entity extraction tools.
- 7.
- 8.
In the first months of 2016, Telegram eventually decided to censor lots of accounts from jihadist supporters.
References
Agarwal, A., Xie, B., Vovsha, I., Rambow, O., & Passonneau, R. (2011). Sentiment analysis of Twitter data. In Proceeding of workshop on languages in social media (pp. 30–38).
Beck, C., & McCue, C. (2009). Predictive policing: What can we learn from Wal-Mart and Amazon about fighting crime in a recession? Police Chief Magazine, 76(11).
Bendler, J., Brandt, T., Wagner, S., & Neumann, D. (2014). Investigating crime-to-twitter relationships in urban environments—facilitating a virtual neighborhood watch. In Proceeding of ECIS 2014.
Berger, J. M., & Morgan, J. (2015). The ISIS Twitter census defining and describing the population of ISIS supporters on Twitter. The Brookings project on U.S. relations with the islamic world.
Bizer, C., Heath, T., & Bernes-Lee, T. (2009). Linked data, the story so far. In IJJWIS. http://linkeddata.org/docs/ijswis-special-issue
Capet, P., & Delavallade, T. (2014). Information Evaluation. Wiley-ISTE.
Casanovas, P., Arraiza, J., Melero, F., Gonzalez-Conejero, J., Molcho, G., & Cuadros, M. (2014). Fighting organized crime through open source intelligence: Regulatory strategies of the CAPER project. In Proceeding of JURIX.
Chau, M., Xu, J., & Chen, H. (2002). Extracting meaningful entities from police narrative reports. In Proceeding of 2002 Annual National Conference on Digital Government Research.
Chen, H., Zeng, D., Atabakhsh, H., Wyzga, W., & Schroeder, J. (2003). COPLINK—managing law enforcement and knowledge. Communications of the ACM, 46(1).
Chew, C., & Eysenbach, G. (2010). Pandemics in the age of Twitter: content analysis of tweets during the 2009 H1N1 outbreak. PLoS One, 5(11).
Cieri, C., Graff, D., Liberman, M., Martey, N., & Strassel, S. (2000). Large, multilingual, broadcast news corpora for cooperative research in topic detection and tracking: The TDT-2 and TDT-3 corpus efforts. In Proceedings of Language Resources and Evaluation Conference.
Cohen, L. (2013). 6 ways law enforcement uses social media to fight crime. http://connectedcops.net/wp-content/uploads/2010/04/6-Ways-Law-Enforcement-Uses-Social-Media-to-Fight-Crime.pdf
Conde-Céspedes, P., Marcotorchino, J. F., & Vienne, E. (2015). Comparison of linear modularization criteria using the relational formalism, an approach to easily identify resolution limit. In Proceeding of EGC-AKDM.
David, O., & Netanyahu, N. (2015). DeepSign: Deep learning for automatic malware signature generation and classification. In IEEE Proceeding.
de Bruin, J., Cocx, T., Kosters, W., Laros, J., & Kok, J. (2006). Data mining approaches to criminal career analysis. In Proceedings of the Sixth International Conference on Data Mining.
De Meo, P., Ferrara, E., Fiumara, G., & Provetti, A. (2011). Generalized Louvain method for community detection in large networks. In Proceedings of the 11th International Conference on Intelligent Systems Design and Applications.
Delavallade, T., Fossier, S., Laudy, C., & Lortal, G. (2016). On the challenges of using social media for crisis management. In Fusion methodologies in crisis management.
Drozdova, K., & Samoilov, M. (2010). Predictive analysis of concealed social network activities based on communication technology choices: Early-warning detection of attack signals from terrorist organizations. Computational and Mathematical Organization Theory, (16).
Europol. (2016). Migrant smuggling in the EU. In Europol public information.
Gerber, S. (2014). Predicting crime using Twitter and kernel density estimation. In Proceeding of Decision Support Systems.
Go, A., Huang, L., & Bhayani, R. (2009). Twitter sentiment analysis. http://www-nlp.stanford.edu/courses/cs224n/2009/fp/3.pdf
Gonçalves, T., & Quaresma, P. (2008). Using linguistic information to classify Portuguese text documents. In Seventh Mexican International Conference on Artificial Intelligence, MICAI ’08.
Iqbal, F., Fung, B., & Debbabi, M. (2012). Mining criminal networks from chat log. In Proceeding of International Conferences on Web Intelligence and Intelligent Agent Technology.
Jurgens, D., Finethy, T., McCorriston, J., Tian, X. Y., & Ruths, D. (2015). Geolocation prediction in Twitter using social networks: A critical analysis and review of current practice. In Proceedings of the 9th International AAAI Conference on Weblogs and Social Media (ICWSM).
Lai, S., Xu, L., Liu, K., & Zhao, J. (2015). Recurrent convolutional neural networks for text classification. In Proceedings of the Twenty-ninth AAAI Conference on Artificial Intelligence.
Leetaru, K., Wang, S., Cao, G., Padmanabhan, A., & Shook, E. (2013). Mapping the global Twitter heartbeat: The geography of Twitter. First Monday, 18(5).
Loten, G., Graeff, E., Ananny, M., Gaffney, D., Pearce, I., & Boyd, D. (2011). The revolutions were tweeted: Information flows during the 2011 Tunisian and Egyptian revolutions. International Journal of Communication, 5.
Oatley, G., Ewart, B., & Zeleznikow, J. (2006). Decision support systems for police: Lessons from the application of data mining techniques to soft forensic evidence. Artificial Intelligence and Law, 14(1).
Pearsall, B. (2010). Predictive policing: The future of law enforcement? NIJ Journal, 266.
Radinsky, K., & Horvitz, E. (2012). Mining the web to predict future events. In Proceeding of WSDM’13.
Rajput, D. S., Thakur, R. S., Thakur, G. S., & Neeraj S. (2012). Analysis of social networking sites using K-mean clustering algorithm. International Journal of Computer & Communication Technology.
Ratcliffe, J. H. (2012). Intelligence-led policing. Willan Publishing.
Scott, J. (2000), Social network analysis. SAGE Publications Ltd.
Spärck Jones, K. (1972). A statistical interpretation of term specificity and its application in retrieval. Journal of Documentation, 28(1), 1972.
Swendsen, A. (2013). Introducing RESINT: A missing and undervalued “INT” in all-source intelligence efforts. International Journal of Intelligence and Counter Intelligence, 26, 4.
Symeonidou-Kastanidou, E. (2007). Towards a new definition of organized crime in the European Union. 15 European Journal of Crime, Crime Law & Criminal Justice, (83–103).
Teulf, P., & Kraxberger, S. (2011). Extracting semantic knowledge from Twitter. In Electronic participation (pp 48–59). Springer.
Teulf, P., Payer, U., Parycek, P., Macintosh, A., & Tambouris, E. (2009). Automated analysis of e-participation data by utilizing associative networks, spreading activation and unsupervised learning. In Proceeding of 1st International Conference on Electronic Participation (pp. 139–150).
Weerkamp, W., & de Rijke, M. (2012). Activity prediction: A Twitter-based exploration. In Proceeding of SIGIR 2012 Workshop on Time-Aware Information Access.
Williams, M., Burnap, P., & Sloan, L. (2016). crime sensing wit big data: The affordance and limitations of using open-source communications to estimate crime patterns. British Journal of Criminology.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2017 Springer International Publishing AG
About this chapter
Cite this chapter
Delavallade, T., Bertrand, P., Thouvenot, V. (2017). Extracting Future Crime Indicators from Social Media. In: Larsen, H., Blanco, J., Pastor Pastor, R., Yager, R. (eds) Using Open Data to Detect Organized Crime Threats. Springer, Cham. https://doi.org/10.1007/978-3-319-52703-1_8
Download citation
DOI: https://doi.org/10.1007/978-3-319-52703-1_8
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-52702-4
Online ISBN: 978-3-319-52703-1
eBook Packages: Law and CriminologyLaw and Criminology (R0)