Organised Crime and Social Media: Detecting and Corroborating Weak Signals of Human Trafficking Online
This paper describes an approach for detecting the presence or emergence of Organised Crime (OC) signals on Social Media. It shows how words and phrases, used by members of the public in Social Media, can be treated as weak signals of OC, enabling informa
- PDF / 2,308,723 Bytes
- 14 Pages / 439.37 x 666.142 pts Page_size
- 86 Downloads / 249 Views
Conceptual Structures Research Group, Sheffield Hallam University, Sheffield, UK 2 Centre of Excellence in Terrorism, Resilience, Intelligence and Organised Crime Research, Communication and Computing Research Centre, Sheffield Hallam University, Sheffield, UK {s.andrews,b.brewster,t.day}@shu.ac.uk
Abstract. This paper describes an approach for detecting the presence or emergence of Organised Crime (OC) signals on Social Media. It shows how words and phrases, used by members of the public in Social Media, can be treated as weak signals of OC, enabling information to be classified according to a taxonomy of OC. Formal Concept Analysis is used to group information sources, according to Crime and Location, thus providing a means of corroboration and creating OC Concepts that can be used to alert police analysts to the possible presence of OC. The analyst is able to ‘drill down’ into an OC Concept of interest, discovering additional information that may be pertinent to the crime. The paper describes the implementation of this approach into a fully-functional prototype software system, incorporating a Social Media Scanning System and a map-based user interface. The approach and system are illustrated using the Trafficking of Human Beings as an example. Real data is used to obtain results that show that weak signals of OC have been detected and corroborated, thus alerting to the possible presence of OC.
1
Introduction
The vociferous proliferation of the Internet, and more recently Social Media, into society and the everyday lives of its citizens has, over the last fifteen or so years, resulted in a sea-change in the behaviours and perceptions we have in relation to the information that is shared freely online [12]. Such behaviour has resulted in the creation of a vast repository of information that holds potential value for police investigations, and the emergence of the open-source researcher as a valuable skill-set within the analytical repertoire of the police and security agencies. Resources such as social media, RSS news feeds, interactive street-maps and online directory services all provide valuable stores of information that can be used to support existing investigative and analytical practices in response to serious and organised crime. This paper focuses on the identification, extraction and corroboration of data from social media using automated data acquisition, c Springer International Publishing Switzerland 2016 O. Haemmerl´ e et al. (Eds.): ICCS 2016, LNAI 9717, pp. 137–150, 2016. DOI: 10.1007/978-3-319-40985-6 11
138
S. Andrews et al.
natural language processing and formal concept analysis (FCA), specifically in order to identify what we will refer to as ‘weak signals’ of human trafficking, and to transform these signals into corroborated alerts linked to the presence or emergence of human trafficking activity. The concept of weak signals is abstracted from the Canadian Criminal Intelligence Service’s (CISC) definitions of primary and secondary indicators [14], and the perception that in reality there is little tang
Data Loading...