CFP last date
20 December 2024
Reseach Article

A Survey on Effective Classification for Text Mining using one-class SVM

by Safdar Sardar Khan, Divakar Singh
International Journal of Computer Applications
Foundation of Computer Science (FCS), NY, USA
Volume 65 - Number 23
Year of Publication: 2013
Authors: Safdar Sardar Khan, Divakar Singh
10.5120/11227-6469

Safdar Sardar Khan, Divakar Singh . A Survey on Effective Classification for Text Mining using one-class SVM. International Journal of Computer Applications. 65, 23 ( March 2013), 35-39. DOI=10.5120/11227-6469

@article{ 10.5120/11227-6469,
author = { Safdar Sardar Khan, Divakar Singh },
title = { A Survey on Effective Classification for Text Mining using one-class SVM },
journal = { International Journal of Computer Applications },
issue_date = { March 2013 },
volume = { 65 },
number = { 23 },
month = { March },
year = { 2013 },
issn = { 0975-8887 },
pages = { 35-39 },
numpages = {9},
url = { https://ijcaonline.org/archives/volume65/number23/11227-6469/ },
doi = { 10.5120/11227-6469 },
publisher = {Foundation of Computer Science (FCS), NY, USA},
address = {New York, USA}
}
%0 Journal Article
%1 2024-02-06T21:20:41.656004+05:30
%A Safdar Sardar Khan
%A Divakar Singh
%T A Survey on Effective Classification for Text Mining using one-class SVM
%J International Journal of Computer Applications
%@ 0975-8887
%V 65
%N 23
%P 35-39
%D 2013
%I Foundation of Computer Science (FCS), NY, USA
Abstract

Data mining techniques have been widely used to find new patterns and knowledge from large amount of data. While Bayesian models were widely used in the early days, more advanced machine learning methods, such as artificial neural networks and support vector machines, have been applied in recent years these techniques are used in different areas. The problem of text mining has gained increasing attention in recent years because of the large amounts of text data, which are created in a variety of social network, web, and other information-centric applications. Unstructured data is the easiest form of data which can be created in any application scenario. As a result, there has been a tremendous need to design methods and algorithms which can effectively process a wide variety of text applications. This paper will provide an overview of the different methods and algorithms which are common in the text domain, with a particular focus on mining methods.

References
  1. S. Wu, C. Yang, and J. Zhou. Clustering-training for datastream mining. Sixth IEEE International Conference onData Mining Workshops, pages 653–656, 2006.
  2. H. Yu, J. Han, and K. Chang. PEBL: web page classificationwithout negative examples. IEEE Transactions on Knowledgeand Data Engineering, 16(1):70–81, 2004.
  3. Y. Zhang and X. Jin. An automatic construction and organizationstrategy for ensemble learning on data streams. ACMSIGMOD Record, 35(3):28–33, 2006.
  4. X. Zhu, X. Wu, and Y. Yang. Dynamic classifier selectionfor effective mining from noisy data streams. Proceedingsof the 4th international conference on Data Mining,(ICDM'04), pages 305–312, 2004.
  5. X. Zhu, P. Zhang, X. Lin, and S. Y. Active Learning fromData Streams. Proceedings of the Sixth International Conferenceon Data Mining, (ICDM'06), 2007.
  6. Yang ZhangOne-class Classification of Text Streams with Concept Drift2008 IEEE International Conference on Data Mining Workshops.
  7. Gabriel Pui Cheong Fung, Jeffrey X. Yu, Member, IEEE Computer Society, Hongjun Lu, and Philip S. Yu, Fellow, IEEEText Classification without Negative Examples Revisitieee transactions on knowledge and data engineering, vol. 18, no. 1, January 2006
  8. Z. Jiawei Han and Micheline Kamber Data mining concepts and techniques book referred third edition 2010
  9. Z. Oxford publication Arun kumar pujari book referred second edition 2011
  10. Data Mining: Concepts and Techniques Second Edition Jiawei Han University of Illinois at Urbana-Champaign Micheline Kamber 2006.
  11. X. Li and B. Liu. Learning from Positive and Unlabeled Examples with Different Data Distributions. ProceedingsofEuropean Conference on Machine Learning (ECML-05), pages 218–229, 2005.
Index Terms

Computer Science
Information Sciences

Keywords

Data mining text mining text categorization partially supervised learning labelling unlabelled data feature selection information filtering SVM