Rough Set-Aided Feature Selection for Automatic Web-Page Classification
Toshiko Wakaki, Hiroyuki Itakura, Masaki Tamura · Web Intelligence · 2004
Recently Web-pages on the World Wide Web are explosively increasing, and it is now required for portal sites such as Yahoo! service having directory-style search engines to classify Web-pages into many categories automatically. This paper investigates how rough settheory can help select relevant features for Web-page classification. Our experimental results show that the combination of the rough set-aided feature selection method and the Support Vector Machine with a linear kernel is quite useful in practice to classify Web-pages into many categories because not only the performance gives acceptable accuracy but also the high dimensionality reduction is achieved without depending on arbitrary thresholds for feature selection.