Data mining in law with adaptive learning techniques

The freely available law on the Internet could be one of the best applications of data mining. The growing complexity of legal rules and the necessary adaptation to user needs requires better instruments than manual browsing and searching interfaces. Our intelligent agent offers information reconnaissance by classifying and describing unknown text corpora of search results. Based on standard agent technology, our research on self-organising maps focuses on adaptive learning techniques for information reconnaissance. The units of the self-organising map are labeled with the most appropriate keywords. The user can choose between the various units in order to refine the next step of research. First results have shown the potential of this approach.