Paul Elzinga

Formal concept analysis in knowledge discovery: a survey

In this paper, we analyze the literature on Formal Concept Analysis (FCA) using FCA. We collected 702 papers published between 2003-2009 mentioning Formal Concept Analysis in the abstract. We developed a knowledge browsing environment to support our literature analysis process. The pdf-files containing the papers were converted to plain text and indexed by Lucene using a thesaurus containing terms related to FCA research. We use the visualization capabilities of FCA to explore the literature, to discover and conceptually represent the main research topics in the FCA community. As a case study, we zoom in on the 140 papers on using FCA in knowledge discovery and data mining and give an extensive overview of the contents of this literature.

A concept discovery approach for fighting human trafficking and forced prostitution

Since the fall of the Iron curtain starting in 1989 in Hungary, millions of Central and Eastern European girls and women have been forced to work in the European sex industry (estimated 175,000 to 200,000 yearly1). In this paper, we present our work with the Amsterdam-Amstelland (Netherlands) police to find suspects and victims of human trafficking and forced prostitution. 266,157 suspicious activity reports were filed by police officers between 2005 and 2009 that contain their observations made during a police patrol, motor vehicle inspection, etc. We used FCA to filter out interesting persons for further investigation and used the temporal variant of FCA to create a visual profile of these persons, their evolution over time and their social environment. We exposed multiple cases of forced prostitution where sufficient indications were available to obtain the permission from the Public Prosecutor to use special investigation techniques. This resulted in a confirmation of their involvement in human trafficking and forced prostitution resulting in actual arrestments being made.

Terrorist threat assessment with formal concept analysis

The National Police Service Agency of the Netherlands developed a model to classify (potential) jihadists in four sequential phases of radicalism. The goal of the model is to signal the potential jihadist as early as possible to prevent him or her to enter the next phase. This model has up till now, never been used to actively find new subjects. In this paper, we use Formal Concept Analysis to extract and visualize potential jihadists in the different phases of radicalism from a large set of reports describing police observations. We employ Temporal Concept Analysis to visualize how a possible jihadist radicalizes over time. The combination of these instruments allows for easy decision-making on where and when to act.

A case of using formal concept analysis in combination with emergent self organizing maps for detecting domestic violence

In this paper, we propose a framework for iterative knowledge discovery from unstructured text using Formal Concept Analysis and Emergent Self Organizing Maps. We apply the framework to a real life case study using data from the Amsterdam-Amstelland police. The case zooms in on the problem of distilling concepts for domestic violence from the unstructured text in police reports. Our human-centered framework facilitates the exploration of the data and allows for an efficient incorporation of prior expert knowledge to steer the discovery process. This exploration resulted in the discovery of faulty case labellings, common classification errors made by police officers, confusing situations, missing values in police reports, etc. The framework was also used for iteratively expanding a domain-specific thesaurus. Furthermore, we showed how the presented method was used to develop a highly accurate and comprehensible classification model that automatically assigns a domestic or non-domestic violence label to police reports.

Formally analysing the concepts of domestic violence

The types of police inquiries performed these days are incredibly diverse. Often data processing architectures are not suited to cope with this diversity since most of the case data is still stored as unstructured text. In this paper Formal Concept Analysis (FCA) is showcased for its exploratory data analysis capabilities in discovering domestic violence intelligence from a dataset of unstructured police reports filed with the Amsterdam-Amstelland police in the Netherlands. From this data analysis it is shown that FCA can be a powerful instrument to operationally improve policing practice. For one, it is shown that the definition of domestic violence employed by the police is not always as clear as it should be, making it hard to use it effectively for classification purposes. In addition, this paper presents newly discovered knowledge for automatically classifying certain cases as either domestic or non-domestic violence. Moreover, it provides practical advice for detecting incorrect classifications performed by police officers. A final aspect to be discussed is the problems encountered because of the sometimes unstructured way of working of police officers. The added value of this paper resides in both using FCA for exploratory data analysis, as well as with the application of FCA for the detection of domestic violence.

Curbing domestic violence: instantiating C–K theory with formal concept analysis and emergent self-organizing maps

We propose a human-centred process for knowledge discovery from unstructured text that makes use of formal concept analysis and emergent self-organizing maps. The knowledge discovery process is conceptualized and interpreted as successive iterations through the concept–knowledge (C–K) theory design square. To illustrate its effectiveness, we report on a real-life case study of using the process at the Amsterdam–Amstelland police in the Netherlands aimed at distilling concepts to identify domestic violence from the unstructured text in actual police reports. The case study allows us to show how the process was not only able to uncover the nature of a phenomenon such as domestic violence, but also enabled analysts to identify many types of anomaly in the practice of policing. We will illustrate how the insights obtained from this exercise resulted in major improvements in the management of domestic violence cases. Copyright

Analyzing Chat Conversations of Pedophiles with Temporal Relational Semantic Systems

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 effective 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 chatterms 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.

Text mining with emergent self organizing maps and multi-dimensional scaling: A comparative study on domestic violence

In this paper we compare the usability of ESOM and MDS as text exploration instruments in police investigations. We combine them with traditional classification instruments such as the SVM and Naive Bayes. We perform a case of real-life data mining using a dataset consisting of police reports describing a wide range of violent incidents that occurred during the year 2007 in the Amsterdam-Amstelland police region (The Netherlands). We compare the possibilities offered by the ESOM and MDS for iteratively enriching our feature set, discovering confusing situations, faulty case labelings and significantly improving the classification accuracy. The results of our research are currently operational in the Amsterdam-Amstelland police region for upgrading the employed domestic violence definition, for improving the training of police officers and for developing a highly accurate and comprehensible case triage model.

An Exploration into the Power of Formal Concept Analysis for Domestic Violence Analysis

The types of police inquiries performed are very diverse in nature and the current data processing architecture is not sufficiently tailored to cope with this diversity. Many information concerning cases is still stored in databases as unstructured text. Formal Concept Analysis is showcased as an exploratory data analysis technique for discovering new knowledge from police reports. It turns out that it provides a powerful framework for exploring the dataset, resulting in essential knowledge for improving current practices. It is shown that the domestic violence definition employed by the police organisation of the Netherlands is not always as clear as it should be, making it hard to use it effectively for classification purposes. In addition, newly discovered knowledge for automatically classifying certain cases as either domestic or non-domestic violence is presented. Moreover, essential techniques for detecting incorrect classifications, performed by police officers, are provided. Finally, some problems encountered because of the sometimes unstructured way of working of police officers are discussed. Both using Formal Concept Analysis for exploratory data analysis and its application on this area are novel enough to make this paper into a valuable contribution to the literature.

Semi-automated knowledge discovery: identifying and profiling human trafficking

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. In-depth 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.