Desktop Text Mining for Open Source Intelligence

Summary form only given. The use of the Internet permeates more and more areas of our daily life. People share and use information in forums and social networks in ways unimaginable just a few years ago. This fantastic medium with global reach, easy access and fast information propagation is, unfortunately, also often a tool for illegal activities. Especially in areas like commercial fraud a huge increase of criminal acts can be observed. To meet these challenges, law enforcement authorities need to build and reinforce capabilities in the domain of OSINT. Characteristics of the Internet like the volume of available data, the plurality of languages and the speed of change make it difficult for public authorities to keep pace. The OPTIMA group of the Joint Research Centre (JRC) does research in the field of open source information extraction and text mining. As part of this research it develops tools which can be used in operational settings. As part of its mission to provide scientific and technical support to EU policies, these tools are provided to law enforcement authorities in Member States of the European Union. The first part of the talk will give an overview of our research in information extraction and text mining. Furthermore, our desktop text mining tool, EMM OSINT Suite, which is in use by law enforcement authorities in Europe, will be presented. Our "lessons learned" with relevance to the research community will be shared. The second part will discuss the impact of general trends in internet technology and research on our work now and in the future.