Study on Classification Algorithm of Multi-subject Text

Authors:
Yu-ping Qin;Qing Ai;Xiu-kun Wang;Xiang-na Li
Affiliations:
Dalian University of Technology, China/ Bohai University, China;Bohai University, China;Dalian University of Technology, China;Bohai University, China
Venue:
SNPD '07 Proceedings of the Eighth ACIS International Conference on Software Engineering, Artificial Intelligence, Networking, and Parallel/Distributed Computing - Volume 02
Year:
2007

Citing 0
Cited 1

One-against-one fuzzy support vector machine classifier: An approach to text categorization

Expert Systems with Applications: An International Journal

Quantified Score

Hi-index	0.00

Visualization

Abstract

One text may belong to multi-class, but it can not be classified by standard SVM and other approaches. In this paper, a multi-subject text classification algorithm based on fuzzy support vector machines is proposed, 1-a-1 method is used to train sub-classifiers. For the sample to be classified, the sub-classifiers are used to obtain membership matrix, and then according to the sum of every line of membership matrix, the subjects that the sample belongs to can be confirmed. The algorithm was tested on Reuters 21578, the experimental results show that the algorithm has higher performance on recall, precision, and F1.