Search
WIT Press


Related conference

BEM/MRM 47

BEM/MRM 47

25-27 September 2024

Seville, Spain

Related Book

Data Mining III

Edited By: A. Zanasi, TEMIS Text Mining Solutions SA, Modena, Italy; C.A. Brebbia, Wessex Institute of Technology, UK; N.F.F. Ebecken, COPPE/UFRJ, Federal University of Rio de Janeiro, Brazil; P. Melli, IBM Italia S.P.A., Italy

Feature Selection Using Support Vector Machines

Price

Free (open access)

Transaction

WIT Transactions on Information and Communication Technologies

Volume

28

Pages

Published

2002

Size

763 kb

Paper DOI

10.2495/DATA020271

Copyright

WIT Press

Author(s)

J Brank, M Grobelnik, N Milic-Frayling & D Mladenic

Abstract

Text categorization is the task of classifying natural language documents into a set of predefine categories. Documents are typically represented by sparse vectors under the vector space model, where each word in the vocabulary is mapped to one coordinate axis and its occurrence in the document gives rise to one nonzero component in the vector representing that document. When training classifiers on large collections of documents, both the time and memory requirements connected with processing of these vectors may be prohibitive. This calls for using a feature selection method, not only to reduce the number of features but also to increase the sparsity of document vectors. We propose a feature selection method based on linear Support Vector Machines (SVMS). First, we train the linear SVM on a subset of training data and retain only those features that correspond to highly weighted components (in absolute value sense) of the normal to the resulting hyperplane that separates positive and negative examples. This reduced feature space is then used to train a classifier over a larger training set because more documents now fit into the same amount of memory. In our experiments we compare the effectiveness of the SVM-based feature selection with that of more traditional feature selection methods, such as odds ratio and information gain, in achieving the desired tradeoff between the vector sparsity and the classification performance. Experimental results indicate that, at the same level of vector sparsity, feature selection based on SVM normals yields better classification performance than odds ratio- or information gain-based feature selection when linear SVM classifiers are used. Introduction Trends towards personalizing information services and client-based applications have increased the importance of effective and efficient document categorization

Keywords



Related conference

BEM/MRM 47

BEM/MRM 47

25-27 September 2024

Seville, Spain

Related Book

Data Mining III

Edited By: A. Zanasi, TEMIS Text Mining Solutions SA, Modena, Italy; C.A. Brebbia, Wessex Institute of Technology, UK; N.F.F. Ebecken, COPPE/UFRJ, Federal University of Rio de Janeiro, Brazil; P. Melli, IBM Italia S.P.A., Italy

Other papers in this volume

Warning (2) : foreach() argument must be of type array|object, null given [in /var/www/dce7ae55-385b-4ffa-8595-3ec5e61ff110/public_html/app/templates/Papers/view.php, line 364]

Keep me updated
Data Mining III

View Book

Other papers in this volume

Data Mining And Soft Computing

Hard Hats For Data Miners: Myths And Pitfalls Of Data Mining

A Method For Knowledge Representation And Discovery Based On Composing And Manipulating Logical Equations

Comparing Dissimilarity Measures For Probabilistic Symbolic Objects

A Data Mining Toolset For Distributed High-performance Platforms

An Integrated Platform For Spatial Data Mining And Interactive Visual Analysis

Combining Data Mining And Optimization For Campaign Management

WIT Press, Ashurst Lodge, Ashurst, Southampton SO40 7AA, UK. Registered in England as a limited company No. 4741634

Copyright 2025 WIT Press All Rights Reserved - Prices are Subject to Change - Returns Policy - Privacy Policy - Site Map