Clustering of Documents via Similarity Measures

0405180 - UIVT-O 20030148 RIV US eng C - Conference Paper (international conference)
Řezanková, H. - Húsek, Dušan - Snášel, V.
Clustering of Documents via Similarity Measures.
Communications in Computing. Las Vegas: CSREA Press, 2003 - (d'Auriol, B.), s. 292-299. ISBN 1-932415-06-8.
[CIC'03. Las Vegas (US), 23.06.2003-26.06.2003]
R&D Projects: GA ČR GA201/01/1192
Institutional research plan: AV0Z1030915
Keywords : similarity measures * proximity matrix * clustering
Subject RIV: BB - Applied Statistics, Operational Research

The paper presents a document analysis case based on similarity measures between two documents. The algorithm is based on the proximity matrix. Initially, the document-tenn matrix is converted into a proximity matrix. The proximity matrix is then processed using standard clustering algorithms. Comparative numerical results are provided.
Permanent Link: http://hdl.handle.net/11104/0125378