On Clustering Validity Measures and the Rough Set Theory
Leticia Arco, Rafael Bello, María Matilde García · 2006
Document clustering has been investigated for use in different areas of text mining and information retrieval. A clustering depends on the chosen clustering algorithm as well as on the algorithm's parameter settings; for that reason it is necessary to find the best among several clustering techniques. However, it is very difficult to evaluate a given clustering of documents. There are external, internal and relative measures. The disadvantage of external measures is the necessity of a human reference classification to evaluate the clustering. In this paper we propose the use of rough-set-based measures for document clustering evaluation, basing our calculations solely on the clustering that has to be evaluated. Thus, two advantages of rough set theory are used: it does not need any preliminary or additional information about data, and it is a tool for use in computer applications in circumstances which are characterized by vagueness and uncertainty (this is the case of document clustering). We illustrate the use of the novel measures.