Analyzing Chat Conversations of Pedophiles with Temporal Relational Semantic Systems

Abstract

Abstract. Grooming is the process by which pedophiles try to find children on the internet for sex-related purposes. In chat conversations they may try to establish a connection and escalate the conversation towards a physical meeting. Till date no good methods exist for quickly analyzing the contents, evolution over time, the present state and threat level of these chat conversations. In this paper we propose a novel method based on Temporal Relational Semantic Systems, the main structure in the temporal and relational version of Formal Concept Analysis. For rapidly gaining insight into the topics of chat conversations we combine a linguistic ontology for chat terms with conceptual scaling and represent the dynamics of chats by life tracks in nested line diagrams. To showcase the possibilities of our approach we used chat conversations of a private American organization which actively searches for pedophiles on the internet.

Semi-automated knowledge discovery: identifying and profiling human trafficking

“…Temporal concept lattices were used in Elzinga, Poelmans, Viaene, Dedene, and Morsing (2010) to create visual profiles of potentially interesting terrorism subjects. Elzinga, Wolff, Poelmans, Viaene, and Dedene (2012) used TCA in combination with nested line diagrams to analyse pedophile chat conversations. Scharfe, Oehrstrom, and Gyori (2009) used a model of branching time in which there are alternative plans for the future corresponding to any possible choice of a person and used it as the basis of an information and communication technology toolset for supporting autism diagnosed teenagers.…”

Time Aware Knowledge Extraction for microblog summarization on Twitter

“…Specifically, this temporal extension has been applied in [23] to search pedophiles on the Internet analyzing chat conversation over the time. Here we adopt a distinct approach by extending FCA introducing fuzziness and temporal correlation among objects, in order to extract temporal dependencies among attributes in the concepts.…”

Advances in Data Mining. Applications and Theoretical Aspects

“…The other four case studies described in this section were a collaboration between KU Leuven and the Amsterdam-Amstelland police. We also investigated how we could offer police investigators quick but thorough insight in long chat conversations (see section 5.5) of potential pedophiles with children (Elzinga et al 2012). An important spin-off of this exercise was the development of a highly accurate automated case labeling system (Poelmans et al 2011a, Poelmans et al 2010a).…”

“…A system which helps officers quickly identify those conversations posing a threat to a child's safety and understand what has been talked about may significantly speed up and improve the efficiency of their work (Elzinga et al 2012). A system which helps officers quickly identify those conversations posing a threat to a child's safety and understand what has been talked about may significantly speed up and improve the efficiency of their work (Elzinga et al 2012).…”