INFO-NS

Intelligent exploitation tools for nonstructured information for the Belgian federal police

Aim

The INFO-NS project provides an objective study to the applicability of mining and decision support tools for the Belgian Federal Police (BFP). More specifically, it is studied how information retrieval, extraction and processing tools can leverage intelligence and decision support by exploiting and linking the information that is contained in vast amounts of free text material with any coexisting, structured but concise data sets that are currently in use.

Partners

The project proposal was submitted by the BFP and is part of the AGORA research program (project AG/GG/101). AGORA is governed by the Belgian Science Policy office. By their expertise in the domain, the project was appointed to the Legal Informatics and Information Retrieval group (LIIR) and the Management Informatics research unit (LIRIS), both of the Katholieke Universiteit Leuven. Two researchers, Jan De Beer (LIIR) and Nishant Kumar (LIRIS), worked in close collaboration on the project.

Strategy

The project has achieved its objective by a thorough evaluation of existing (commercial) products of leading players in the field of text and data mining applications. The final evaluation report (confidential version) contains a founded recommendation on the software that is - amongst the evaluated products - considered most suitable in addressing the identified key requirements of the BFP. Envisioning a large-scale deployment of the software, necessary and recommended changes to the existing data management infrastructure are formulated as well.

Results

The researchers have reached the objectives of the INFO-NS project. Their findings and results can be used in a motivated selection and a successful implementation of an exploitation tool for searching and mining the information sources (documents) of the BFP. The public version of the summary report is available as a PDF document.



Period From 2004-10-01 to 2005-10-31.
Financed by Belgian Science Policy
Supervised by Marie-Francine Moens
Staff Jan De Beer
Contact Marie-Francine Moens

Publications

  1. DE BEER, J., KUMAR, N., MOENS, M.-F & VANTHIENEN, J. (2006). Assessing the State of the Art of Commercial Tools for Unstructured Information Exploitation. In Proceedings of the 9th International Conference on Business Information Systems (Springer Lecture Notes in Computer Science). 2006
  2. DE BEER, J & MOENS, M.-F. (2006). Rpref - A Generalization of Bpref towards Graded Relevance Judgments. In Proceedings of the 29th Annual International ACM SIGIR Conference on Research & Development in Information Rerieval. 2006
  3. KUMAR, N., DE BEER, J., VANTHIENEN J. & MOENS, M.-F. Evaluation of Intelligent Exploitation Tools for Non-structured Police Information. In Proceedings of the ICAIL 2005 Workshop on Data Mining, Information Extraction and Evidentiary Reasoning for Law Enforcement and Counter-terrorism (pp. 1-7). 2005
  4. KUMAR, N., DE BEER, J. , VANTHIENEN, J. & MOENS, M.-F. Evaluation of Intelligent Information Retrieval Tools for Unstructured Police Case Reports. In Proceedings Conferentie Informatiewetenschap 2005. 2005
  5. KUMAR, N., DE BEER, J., VANTHIENEN, J., MOENS, M.-F. Evaluation of information retrieval and text mining tools on automatic named entity extraction. In Proceedings of the Intelligence and Security Informatics Conference, San Diego, California (USA), May 23-24 (Lecture Notes in Computer Science, vol. 3975). 2006
  6. KUMAR, N., DE BEER, J., VANTHIENEN, J., MOENS, M.-F. Intelligent information retrieval tools for police. In Proceedings of the Intelligence and Security Informatics Conference, San Diego, California (USA), May 23-24 (Lecture Notes in Computer Science, vol. 3975). 2006
  7. KUMAR, N., DE BEER, J., VANTHIENEN, J., MOENS, M.-F. Multi-criteria evaluation of information retrieval tools. In Proceedings of the 8th International Conference on Enterprise Information Systems (ICEIS 2006), Paphos (Cyprus), May 23-27. 2006


Back to all projects