ProbMap – A probabilistic approach for mapping large document collections

Article type: Research Article

Authors: Hofmann, Thomas

Affiliations: Department of Computer Science, Brown University, Box 1910, Providence, RI 02912, USA. E-mail: th@cs.brown.edu

Abstract: The visualization of large text databases and document collections is an important step towards more flexible and interactive types of information access and retrieval. This paper presents a probabilistic approach which combines a statistical, model-based analysis of a given set of documents with a topological visualization principle. Our method can be utilized to derive topic maps, which represent topical information by characteristic keyword distributions arranged in a two-dimensional spatial layout. Combined with multi-resolution techniques this provides a three-dimensional space for interactive information navigation in large text collections.

Keywords: information retrieval, data mining, machine learning, latent class models, data visualization, self-organizing map

DOI: 10.3233/IDA-2000-4205

Journal: Intelligent Data Analysis, vol. 4, no. 2, pp. 149-164, 2000