Improving Clustering Accuracy using Feature Extraction Method
Keywords:
Clustering, Euclidean Distance, Document frequency, Dimensionality reduction, Principal componentsAbstract
Clustering is the technique employed to group documents containing related information into clusters, which facilitates the allocation of relevant information. Clustering performance is mostly dependent on the text document features. The first challenge concerns difficulty with identifying significant term features to represent original content by considering the hidden knowledge. The second challenge is related to reducing data dimensionality without losing essential information. Clustering techniques were proposed to use feature extraction methods Principal Component Analysis (PCA) and Kernel Principal Component Analysis (KPCA) to improve the clustering efficiency and quality. Documents are pre-processed, converted to vector space model and then clustered using the proposed algorithm. The goal of this work is to design a suitable model for clustering text document that is capable of improving clustering performance. In this paper, the problems are discussed with empirical evidence. Experimental results show that the proposed method is effective for the text clustering task.
References
C. Boutsidis, M.W. Mahoney, P. Drineas,"Unsupervised Feature Selection for the k-Means clustering problem", In the NIPS`09 Proceedings of the 22nd International Conference on Neural Information Processing Systems, Canada, pp.153-161, 2009.
D. Greene, P. Cunningham, "Practical Solutions to the Problem of Diagonal Dominance in Kernel Document Clustering", In the 23rd International Conference on Machine Learning, Pittsburgh, PA, pp.377-384, 2006.
Z. Miner, L. Csat, "Kernel PCA Based Clustering for Inducing Features in text Categorization", In the ESANN`2007 Proceedings- European Symposium on Artificial Neural Networks, Bruges,Belguim., pp.349-354, 2007.
R. Mall, J.A.K.Suykens,"Kernel Spectral Document Clustering Using Unsupervised Precision-Recall Metrics.", 2015 International Joint Conference on Neural Network,Killarney, Ireland, pp. 1-7, 2015.
R. Jenssen, T.Eltoft, M.Girolami and D. Erdogmus ,"Kernel Maximum Entropy Data Transformation and an Enhanced Spectral Clustering Algorithm.", In the NIPS`06 Proceedings of the 19th International Conference on Neural Information Processing Systems, Canada, pp.633-640, 2006.
T. Shi, M. Belkin, B. Yu, “Data spectroscopy: eigenspaces of convolution operators and clustering”, The Annals of Statistics, Vol. 37, No.6B, pp.3960-3984, 2009.
L.Kaufmann, “Advances in Kernel Methods — Support Vector Learning -Solving the quadratic programming problem arising in support vector classification, MIT Press, Cambridge, MA, pp.147–168, 1999.
Y.Yang, J.O. Pedersen, "A Comparative study of feature selection in Text Categorization", In the Proceedings of the Fourteenth International Conference on Machine Learning (ICML`97), USA, pp.412-420, 1997.
I. Feinerer, K.Hornik, D. Meyer, "Text Mining Infrastructure in R”, Journal of Statistical Software, Vol.25, Issue 5, pp.1-54, 2008..
A. Karatzoglou, A. Smola, K. Hornik, A. Zeileis, "kernlab - An S4 Package for Kernel Methods in R", Journal of Statistical Software Vol.11, Issue 9, pp.1-20, 2004.
Downloads
Published
How to Cite
Issue
Section
License
This work is licensed under a Creative Commons Attribution 4.0 International License.
Authors contributing to this journal agree to publish their articles under the Creative Commons Attribution 4.0 International License, allowing third parties to share their work (copy, distribute, transmit) and to adapt it, under the condition that the authors are given credit and that in the event of reuse or distribution, the terms of this license are made clear.
