A Comparative Study on Feature Selection in Chinese Text Classification Problem

Abstract:

Information explosion brings lots of challenges to text classification. The dimension disaster led to a sharp increase of computational complexity and lower classification accuracy. Therefore, it is critical to use feature selection techniques before actual classification. Automatic classification of English text has been researched for many years, but little on Chinese text. In this paper, several classic feature selection methods, namely TF, IG and CHI, are compared on classifying Chinese text. Meanwhile, we take imbalanced data into consideration in the paper. Experimental results show that CHI performed better than IG and TF when the dataset is imbalanced, but no obvious difference on balanced data.

• Periodical: Applied Mechanics and Materials (Volumes 380-384)
• Pages: 2854-2857
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.380-384.2854
• Online since: August 2013
• Authors: Hu Li, Peng Zou, Wei Hong Han
• Keywords: Feature Selection, Imbalanced Data, Text Classification

References

[1] J. Furnkranz: Round Robin classification. J. Mach. Learn., vol. 2 (2002), pp.721-747.

[2] S. L. Lam and D. L. Lee: Feature Reduction for Neural Network Based Text Categorization, Proc. 6th International Conference on Database Systems for Advanced Applications, IEEE (1999), pp.195-202.

DOI: 10.1109/dasfaa.1999.765752

[3] Y. Yang and J. P. Pedersen: A Comparative Study on Feature Selection in Text Categorization, Proc. 14th International Conference on Machine Learning, Morgan Kaufmann, (1997), pp.412-420.

[4] W. Zhang, T. Yoshida and X. Tang: A comparative study of TF*IDF, LSI and multi-words for text classification, J. Expert Systems with Applications, vol. 38, (2011), pp.2758-2765.

DOI: 10.1016/j.eswa.2010.08.066

[5] Y. L. Hung: Efficient classifiers for multi-class classification problems, J. Decision Support Systems, vol. 53 (2012), pp.473-481.

DOI: 10.1016/j.dss.2012.02.014

[6] K. S. Jones: A statistical interpretation of term specificity and its application in retrieval, J. Documentation, vol. 28 (1972), pp.11-21.

DOI: 10.1108/eb026526

[7] J. Nathalie and S. Shaju: The class imbalance problem: A systematic study, J. Intelligent Data Analysis, vol. 6 (2002), pp.429-449.

[8] H. He and E. A. Garcia: Learning from imbalanced data, J. IEEE Trans. Knowl. Data Eng., vol. 21 (2009), pp.1263-1284.

DOI: 10.1109/tkde.2008.239

[9] A. K. Daniel, O. Daniela and R. Christian: Analyzing document collections via context-aware term extraction, Proc. 14th international conference on Applications of Natural Language to Information Systems, Springer (2009), pp.154-168.

DOI: 10.1007/978-3-642-12550-8_13