Websom for Textual Data Mining

  • Authors:
  • Krista Lagus;Timo Honkela;Samuel Kaski;Teuvo Kohonen

  • Affiliations:
  • Neural Networks Research Centre, Helsinki University of Technology, P.O. Box 2200, FIN-02015 HUT, Finland (*Corresponding author: Krista.Lagus@hut.fi);Neural Networks Research Centre, Helsinki University of Technology, P.O. Box 2200, FIN-02015 HUT, Finland;Neural Networks Research Centre, Helsinki University of Technology, P.O. Box 2200, FIN-02015 HUT, Finland;Neural Networks Research Centre, Helsinki University of Technology, P.O. Box 2200, FIN-02015 HUT, Finland

  • Venue:
  • Artificial Intelligence Review - Special issue on data mining on the Internet
  • Year:
  • 1999

Quantified Score

Hi-index 0.00

Visualization

Abstract

New methods that are user-friendly and efficient are needed for guidanceamong the masses of textual information available in the Internet and theWorld Wide Web. We have developed a method and a tool called the WEBSOMwhich utilizes the self-organizing map algorithm (SOM) for organizing largecollections of text documents onto visual document maps. The approach toprocessing text is statistically oriented, computationally feasible, andscalable – over a million text documents have been ordered on a single map.In the article we consider different kinds of information needs and tasksregarding organizing, visualizing, searching, categorizing and filteringtextual data. Furthermore, we discuss and illustrate with examples howdocument maps can aid in these situations. An example is presented wherea document map is utilized as a tool for visualizing and filtering a stream ofincoming electronic mail messages.