List based matching algorithm for classifying news articles in NewsPage.com

Author

Jo, Taeho ; Yeom, Gwyduk

Author_Institution

IT Convergence, KAIST, Daejon

fYear

2008

fDate

2-4 June 2008

Firstpage

1

Lastpage

5

Abstract

This research proposes an alternative approach to machine learning based ones for categorizing news articles given as in plain texts. In order to use one of machine learning based approaches for the task, documents should be encoded into numerical vectors; it causes two problems: huge dimensionality and sparse distribution. The proposed approach is intended to address the two problems. In other words, the two problems are avoided by encoding a document or documents into a table, instead of numerical vectors. Therefore, the goal of the research is to improve the performance of text categorization by solving the two problems.

Keywords

Web sites; learning (artificial intelligence); pattern classification; text analysis; NewsPage.com; list based matching algorithm; machine learning; news article categorization; news article classification; sparse distribution; text categorization; Convergence; Encoding; Kernel; Machine learning; Machine learning algorithms; Nearest neighbor searches; Niobium; Support vector machine classification; Support vector machines; Text categorization;

fLanguage

English

Publisher

ieee

Conference_Titel

System of Systems Engineering, 2008. SoSE '08. IEEE International Conference on

Conference_Location

Singapore

Print_ISBN

978-1-4244-2172-5

Electronic_ISBN

978-1-4244-2173-2

Type

conf

DOI

10.1109/SYSOSE.2008.4724142

Filename

4724142