A Hybrid Approach to Error Reduction of Support Vector Machines in Document Classification

Author

Tae, Yoon-Shik ; Son, Jeong Woo ; Kong, Mi-Hwa ; Lee, Jun-Seok ; Park, Seong-Bae ; Lee, Sang-Jo

Author_Institution

Dept. of Comput. Eng., Kyungpook Nat. Univ., Daegu

fYear

2006

fDate

10-12 April 2006

Firstpage

501

Lastpage

506

Abstract

In this paper, we present a hybrid method of support vector machine and k-nearest neighbor to improve the performance of automatic text classification. The proposed methods first classify a given document using SVM which shows the best performance in text classification, and then is reinforced by k-NN for the documents that are not confidently classified by SVM. According to the experimental results, the hybrid method achieves the F-score of 85.2, which implies that the hybrid method outperforms SVM alone

Keywords

pattern classification; support vector machines; text analysis; automatic text classification; document classification; error reduction; k-nearest neighbor; support vector machines; Computer errors; Hybrid power systems; Information technology; Support vector machine classification; Support vector machines;

fLanguage

English

Publisher

ieee

Conference_Titel

Information Technology: New Generations, 2006. ITNG 2006. Third International Conference on

Conference_Location

Las Vegas, NV

Print_ISBN

0-7695-2497-4

Type

conf

DOI

10.1109/ITNG.2006.10

Filename

1611642

Link To Document

https://search.isc.ac/dl/search/defaultta.aspx?DTC=49&DC=3473983