@inproceedings{fd8eecd43d92424a8c57dc9c4edce513,
title = "Integrating incremental feature weighting into na{\"i}ve bayes text classifier",
abstract = "In the real-world operational environment, text classification systems should handle the problem of incomplete training set and no prior knowledge of feature space. In this regard, the most appropriate algorithm for operational text classification is the Na{\"i}ve Bayes since it is easy to incrementally update its pre-learned classification model and feature space. Our work mainly focuses on improving Na{\"i}ve Bayes classifier through feature weighting strategy. The basic idea is that parameter estimation of Na{\"i}ve Bayes can consider the degree of feature importance as well as feature distribution. In addition, we have extended a conventional algorithm for incremental feature update for developing a dynamic feature space in operational environment. Through experiments using the Reuters-21578 and the 20Newsgroup benchmark collections, we show that the traditional multinomial Na{\"i}ve Bayes classifier can be significantly improved by X2-statistic based feature weighting.",
keywords = "Feature selection, Feature weighting, Na{\"i}ve Bayes classifier, Text classification, X-statistic",
author = "Kim, {Han Joon} and Jaeyoung Chang",
year = "2007",
doi = "10.1109/ICMLC.2007.4370315",
language = "English",
isbn = "142440973X",
series = "Proceedings of the Sixth International Conference on Machine Learning and Cybernetics, ICMLC 2007",
pages = "1137--1143",
booktitle = "Proceedings of the Sixth International Conference on Machine Learning and Cybernetics, ICMLC 2007",
note = "6th International Conference on Machine Learning and Cybernetics, ICMLC 2007 ; Conference date: 19-08-2007 Through 22-08-2007",
}