Semi-automated knowledge discovery: identifying and profiling human trafficking

Abstract

We propose an iterative and human-centred knowledge discovery methodology based on formal concept analysis. The proposed approach recognizes the important role of the domain expert in mining real-world enterprise applications and makes use of specific domain knowledge, including human intelligence and domain-specific constraints. Our approach was empirically validated at the Amsterdam-Amstelland police to identify suspects and victims of human trafficking in 266,157 suspicious activity reports. Based on guidelines of the Attorney Generals of the Netherlands, we first defined multiple early warning indicators that were used to index the police reports. Using concept lattices, we revealed numerous unknown human trafficking and loverboy suspects. Indepth investigation by the police resulted in a confirmation of their involvement in illegal activities resulting in actual arrestments been made. Our human-centred approach was embedded into operational policing practice and is now successfully used on a daily basis to cope with the vastly growing amount of unstructured information.

International responses to human trafficking: The Ghanaian experience

“…The findings on the nature and scope of the menace revealed that the Ghanaian situation was similar to the reported cases of human trafficking from many different parts of the world as reported by Shelley and Lee (2007), Kempadoo et al (2015), and US Department of State (2003). In many different parts of the world including New York (Nack, 2010), Netherlands (Poelmana et al, 2012), and Malaysia (Stanslas, 2010), the police service was engaged in multi-dimensional approaches to limit the scope of human trafficking but the findings from this study indicated that the government of Ghana and GPS had not put in much effort to limit the scope of human trafficking in Ghana as reported by Aning et al (2013).…”

“…In some countries such as Australia, the police consider people smuggling as a threat to national security (Pickering, 2004). In Netherlands, the operational practice of the police uses human-centered approach to gather unstructured information that reveals many unknown human trafficking practices (Poelmana et al, 2012). In Malaysia, the major human trafficking problem confronting the police concerns trans-border security that prompted the police to strengthen their maritime governance to control the influx of illegals to curtail public corruption fueled by human trafficking (Stanslas, 2010).…”

Unsupervised Anomaly Detection for Discrete Sequence Healthcare Data

“…In [21], authors have investigated a problem of human trafficking, which requires detection and interpretability, so they applied used Formal Concept Analysis. In [4], authors also have investigated this algorithm, but for specific sequences.…”

Introduction to Formal Concept Analysis and Its Applications in Information Retrieval and Related Fields

“…In [37], we proposed an iterative and human-centred knowledge discovery methodology based on FCA. The proposed approach recognises the important role of the domain expert in mining real-world enterprise applications and makes use of specific domain knowledge, including human intelligence and domain-specific constraints.…”