Text classification toward a scientific forum

Abstract

Text mining, also known as discovering knowledge from the text, which has emerged as a possible solution for the current information explosion, refers to the process of extracting non-trivial and useful patterns from unstructured text. Among the general tasks of text mining such as text clustering, summarization, etc, text classification is a subtask of intelligent information processing, which employs unsupervised learning to construct a classifier from training text by which to predict the class of unlabeled text. Because of its simplicity and objectivity in performance evaluation, text classification was usually used as a standard tool to determine the advantage or weakness of a text processing method, such as text representation, text feature selection, etc. In this paper, text classification is carried out to classify the Web documents collected from XSSC Website (http://www.xssc.ac.cn). The performance of support vector machine (SVM) and back propagation neural network (BPNN) is compared on this task. Specifically, binary text classification and multi-class text classification were conducted on the XSSC documents. Moreover, the classification results of both methods are combined to improve the accuracy of classification. An experiment is conducted to show that BPNN can compete with SVM in binary text classification; but for multi-class text classification, SVM performs much better. Furthermore, the classification is improved in both binary and multi-class with the combined method.

Keywords

Text classification / SVM / BPNN / Xiangshan Science Conference

References

[1] Adeva J.J.G., Atxa J.M.P.. Intrusion detection in Web applications using text mining. Engineering Applications of Artificial Intelligence, 2007, 20(1): 555-566.

[2] Cristianini N., Taylor J. S.. An Introduction to Support Vector Machines and Other Kernel-Based Learning Methods, 2000, New York: Cambridge University Press.

[3] Hiissa, M. et al. (2007). Towards automated classification of intensive care nursing narratives. International Journal of Medical Informatics. In Press

[4] Han J.W., Kamberl M.. Data Mining Concepts and Techniques, 2006, 2 San Francisco: Morgan Kaufmann Publishers.

[5] Jacob K., Stephen P., Michael S., Alexander R.. Ontology based text indexing and querying for the semantic web. Knowledge-Based Systems, 2006, 19: 744-754.

[6] John D., Dieter F., Frank V. H.. Towards the Semantic Web: Ontology-Driven Knowledge Management, 2003, New York: John Wiley & Sons, Ltd.

[7] Liu Y.J., Tang X.J.. Developed computerized tools based on mental models for creativity support. International Journal of Knowledge and System Sciences, 2006, 3(3): 34-40.

[8] Liu, Y.J., Tang, X.J. & Li, Z. H. (2005). A preliminary analysis of XSSC as transdisciplinary argumentation. In: Liu, S.F., et al, (eds.), New Development of Management Science and Systematic Science (Proceeding of The 8th Youth Conference on Management Science and System Science). 35–40, Nanjing, May 7–10, Press of HeHai University. (in Chinese)

[9] Luhn H.P.. The automatic creation of literature abstracts. IBM Journal of Research and Development, 1958, 2(2): 159-165.

[10] Mulier F.. Vapnik-Chervonenkis (VC) learning theory and its application. IEEE Transaction on Neural Networks, 1999, 10(5): 5-7.

[11] Ou G., Murphey Y.. Multi-class classification using neural networks. Pattern Recognition, 2007, 40: 4-18.

[12] Rennie, J. D. & Rifkin, R. (2001). Improving Multi-class Text Classification with the Support Vector Machine. Master’s thesis. MIT

[13] Rumelhart D. E., Hinton G. E., Williams R. J.. Learning internal representations by error propagation. Parallel Distributed Processing, Exploitations in the Microstructure of Cognition, 1986, Cambridge, MA: MIT Press 318-362.

[14] Stefan, R. (2000). mySVM-Manual. Available via DIALOG. http://www-ai.cs. unidortmund.de /software/ mysvm

[15] Tang X.J., Liu Y.J., Zhang W.. Khosla R. J. H., Jain L. C.. Computerized support for idea generation during knowledge creating process. Knowledge-Based Intelligent Information & Engineering Systems (Proceedings of KES’2005, Part IV), Lecture Notes on Artificial Intelligence, 2005, Springer-Verlag: Berlin Heidelberg 437-443.

[16] Wahba, G. (1999). Support vector machines, reproducing kernel Hilbert spaces and their randomized GACV. In: Advances in Kernel Methods-Support Vector Learning, 69-88. MIT Press

[17] Weiss S.M., Indurkhya N., Zhang T., Damerau F.. Text mining-Predictive Methods for Analyzing Unstructured Information, 2005, New York: Springer Science and Business Media, Inc..

[18] Weston, J. & Watkins, C. (1999). Multi-class support vector machines. In Proceedings ESANN. Brussels

[19] Yang Y.M., Lin X.. A re-examination of text categorization methods. Proceedings on the 22nd Annual International ACM SIGIR Conference on Research and Development in Information Retrieval, 1999, Berkeley: California, USA 42-49.

[20] Zhang Y.Y., Jiao J.X.. An associative classification based recommendation system for personalization in B2C e-commerce application. Expert Systems with Applications, 2007, 33(1): 357-367.

[21] Zhang, W. (2006). Information support tool based on web text mining and its application. Master thesis. Academy of Mathematics and Systems Science, Chinese Academy of Sciences.(in Chinese)

[22] Zhang W., Tang X.J.. Web text mining on a scientific forum. International Journal of Knowledge and System Sciences, 2006, 3(4): 51-59.

[23] Zhang W., Tang X.J.. Information Support tool based on web content mining. Journal of Management Review, 2006, 18(9): 21-26.

[24] Zipf G. K.. Human Behaviour and the Principle of Least Effort, 1949, Cambridge, Massachusetts: Addison-Wesely