%0 Conference Paper %1 lewis1992featureselection %A Lewis, David D. %B HLT '91: Proceedings of the workshop on Speech and Natural Language %C Morristown, NJ, USA %D 1992 %I Association for Computational Linguistics %K classification imported msc representation %P 212--217 %R http://dx.doi.org/10.3115/1075527.1075574 %T Feature selection and feature extraction for text categorization %U http://portal.acm.org/citation.cfm?id=1075574 %X The effect of selecting varying numbers and kinds of features for use in predicting category membership was investigated on the Reuters and MUC-3 text categorization data sets. Good categorization performance was achieved using a statistical classifier and a proportional assignment strategy. The optimal feature set size for word-based indexing was found to be surprisingly low (10 to 15 features) despite the large training sets. The extraction of new text features by syntactic analysis and feature clustering was investigated on the Reuters data set. Syntactic indexing phrases, clusters of these phrases, and clusters of words were all found to provide less effective representations than individual words. %@ 1-55860-272-0

@inproceedings{lewis1992featureselection, abstract = {The effect of selecting varying numbers and kinds of features for use in predicting category membership was investigated on the Reuters and MUC-3 text categorization data sets. Good categorization performance was achieved using a statistical classifier and a proportional assignment strategy. The optimal feature set size for word-based indexing was found to be surprisingly low (10 to 15 features) despite the large training sets. The extraction of new text features by syntactic analysis and feature clustering was investigated on the Reuters data set. Syntactic indexing phrases, clusters of these phrases, and clusters of words were all found to provide less effective representations than individual words.}, added-at = {2007-09-05T15:00:54.000+0200}, address = {Morristown, NJ, USA}, author = {Lewis, David D.}, biburl = {https://www.bibsonomy.org/bibtex/2bac9afca11c1dbd672e969bed8fa3a26/ngrandy}, booktitle = {HLT '91: Proceedings of the workshop on Speech and Natural Language}, description = {Feature selection and feature extraction for text categorization}, doi = {http://dx.doi.org/10.3115/1075527.1075574}, interhash = {88d5f7b14dd37c51947e864b1e93cb4c}, intrahash = {bac9afca11c1dbd672e969bed8fa3a26}, isbn = {1-55860-272-0}, keywords = {classification imported msc representation}, location = {Harriman, New York}, pages = {212--217}, publisher = {Association for Computational Linguistics}, timestamp = {2007-09-05T15:00:55.000+0200}, title = {Feature selection and feature extraction for text categorization}, url = {http://portal.acm.org/citation.cfm?id=1075574}, year = 1992 }