Title: Unsupervised Topic Detection in document collections: an application in marketing and business journals
Authors: Reinhold Decker, Soren W. Scholz
Addresses: Department of Business Administration and Economics, Bielefeld University, P.O. Box 100131, 33501 Bielefeld, Germany. ' Department of Business Administration and Economics, Bielefeld University, P.O. Box 100131, 33501 Bielefeld, Germany
Abstract: The rapid increase of publications in marketing and related areas increasingly hampers the realisation of a general idea of what is |hot| in the respective fields of interest. Topic Detection (TD), based on unsupervised text clustering, is a promising approach to tackle this problem. We introduce a new methodology that facilitates the determination of the number of topics discussed in a given text collection. By applying this approach to a text corpus which includes 12 international marketing and business journals we identify hot spots in marketing science. The approach may help both scientists and practitioners to systematically discover topics in digital information environments, as provided by the internet for instance.
Keywords: business intelligence; environmental scanning; marketing science; text mining; topic detection; unsupervised clustering; data mining; document collections; marketing journals; business journals; digital information; internet.
International Journal of Business Intelligence and Data Mining, 2007 Vol.2 No.3, pp.347 - 364
Available online: 19 Oct 2007 *Full-text access for editors Access for subscribers Purchase this article Comment on this article