Conference proceedings article
Explaining Text Clustering Results using Semantic Structures



Publication Details
Authors:
Stumme, G.; Hotho, A.
Editor:
Lavra\v{c} Nada, Gamberger Dragan, Todorovski BlockeelLjupco Hendrik
Publisher:
Springer
Place:
Heidelberg
Publication year:
2003
Pages range:
217-228
Book title:
Knowledge Discovery in Databases: PKDD 2003, 7th European Conference on Principles and Practice of Knowledge Discovery in Databases
Title of series:
LNAI
Volume number:
2838

Abstract
Common text clustering techniques offer rather poor capabilitiesfor explaining to their users why a particular result has beenachieved. They have the disadvantage that they do not relatesemantically nearby terms and that they cannot explain howresulting clusters are related to each other. In this paper, we discuss a way of integrating a large thesaurus and the computation of lattices of resulting clusters into common text clustering in order to overcome these two problems.As its major result, our approach achieves an explanation using anappropriate level of granularity at the concept level as well asan appropriate size and complexity of the explaining lattice ofresulting clusters.


Keywords
analysis, clustering, concept, fca, formal, ontologies, semantic, semantics, text

Last updated on 2019-25-07 at 12:27