PASCAL - Pattern Analysis, Statistical Modelling and Computational Learning

Recherche d'information inattendue pour la veille technologique.
Christine Largeron and François Jacquenet
Revue des Nouvelles Technologies de l'Information. Volume Numéro spécial Fouilles de Données complexes, 2005.

Abstract

In the domain of business intelligence, computers are useful for extracting scientific or technological information that may be relevant to companies. Moreover, in this context, the aim is to find some unexpected knowledge that may appear with a low frequency. In order to automatically discover some useful knowledge from databases (patents, research publications,etc) we propose to use text mining techniques. Nevertheless, most of these techniques can help finding some frequent information instead of unexpected one, thus, they are not well suited for business intelligence that requires a specific approach. To this end, we have designed several new knowledge discovery measures and integrated them in the UnexpectedMiner System that is able to extract some novel information that may be of interest for the user. We have experimented UnexpectedMiner on a database of scientific abstracts and reported the impact of the various measures on the efficiency of the system.

PDF - Archive staff only - Requires Adobe Acrobat Reader or other PDF viewer.
EPrint Type:Article
Project Keyword:Project Keyword UNSPECIFIED
Subjects:Information Retrieval & Textual Information Access
ID Code:1541
Deposited By:Christine Largeron
Deposited On:28 November 2005