Blog classification: Adding linguistic knowledge to improve the K-NN algorithm

Abstract

Blogs are interactive and regularly updated websites which can be seen as diaries. These websites are composed by articles based on distinct topics. Thus, it is necessary to develop Information Retrieval approaches for this new web knowledge. The first important step of this process is the categorization of the articles. The paper above compares several methods using linguistic knowledge with k-NN algorithm for automatic categorization of weblogs articles. © 2008 International Federation for Information Processing.