Hits:

Indexed by:期刊论文

Date of Publication:2007-03-01

Journal:Journal of Computational Information Systems

Included Journals:EI

Volume:3

Issue:3

Page Number:1307-1312

ISSN No.:15539105

Abstract:Text classification is a process of automatically assigning predefined categories to free text, which is very important to information retrieval and web content mining. The most important step is to extract the accurate rules for classification. In this paper, a new method of rule extraction for text categorization based on Pattern Aggregation and Rough Set is proposed. After the texts are preprocessed, the pattern aggregation which merges some features that have the approximate proportion of contribution for categorization method as a new feature is used to reduce feature dimension, and then rough set which is a powerful tool to discover patterns and extract rules is applied to deeper dimension reduction and rule extraction. Experiments conducted on the Reuters 21578 dataset indicate that the combination approach provides an improved and scalable method for Rule Extraction.