Proposal of classification technique of Web site by keyword analysis and application to real data

Abstract

Websites are classified into various categories so that it is shown in the directory-based search engine like Yahoo! Japan. Nouns the feature in each category should exist because Website in the category has contents related to the category. If nouns the feature in such each category can be used, websites can be classified into categories. In this paper, it proposes the automatic website classification technique by the similarity with the category based on the score of all nouns extracted in websites, using the appearance frequency of each category. The effectiveness is verified from 10 categories in the directory-based search engine Yahoo! Japan.