A method based on manifold learning and Bagging for text classification

Author

Li, FengGang ; Fan, JiLi ; Wang, Li ; Zhang, HuLin ; Duan, Rui

Author_Institution

Sch. of Manage., Hefei Univ. of Technol., Hefei, China

fYear

2011

fDate

8-10 Aug. 2011

Firstpage

2713

Lastpage

2716

Abstract

In order to solve the problem of high dimension in text classification, the paper proposes a method based on manifold learning and Bagging for text classification which imports manifold learning algorithm for dimension reduction. And Bagging algorithm is introduced when training classifier to improve the accuracy of text classification. Experimental results demonstrate that effect of text dimension reduction by manifold learning algorithm in the pretreatment of text classification is better, and the performance of the classifier has improved significantly.

Keywords

learning (artificial intelligence); pattern classification; text analysis; classifier training; dimension reduction; high dimension problem; manifold Bagging algorithm; manifold learning algorithm; text classification; text dimension; Bagging; Classification algorithms; Euclidean distance; Manifolds; Support vector machine classification; Text categorization; Training; Bagging; Isomap; dimension reduction; manifold learning;

fLanguage

English

Publisher

ieee

Conference_Titel

Artificial Intelligence, Management Science and Electronic Commerce (AIMSEC), 2011 2nd International Conference on

Conference_Location

Deng Leng

Print_ISBN

978-1-4577-0535-9

Type

conf

DOI

10.1109/AIMSEC.2011.6010811

Filename

6010811