Answers are grounded in this paper and cite their sources.
Feature selection is an essential preprocessing step for classifiers with high dimensional training corpus. Features for text categorization include words, phrases, sentences or distribution of words. The complexity of classifying documents to related categories is on higher scale in comparison with unrelated categories. A feature selection algorithm based on chi-square statistics, have been proposed for Nave Bayes classifier. The proposed feature selection method identifies the related features for a class and determines the type of dependency between the feature and category. In this paper, the proposed method ascertains related phrases and words as features. A comparison of the conventional chi-square method is made with the proposed method. Experiments were conducted with randomly chosen training documents from one unrelated and five closely related categories of 20Newsgroup Benchmarks. It is observed that the proposed method has better precision and recall.
No takes yet. Share an insight, caveat, or question.
Meena et al. (2010) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: