Feature Weighting Method Based on Real-Coded Genetic Algorithm in Text Categorization

Feature weighting technique can improve the accuracy of text categorization, TF-IDF is a generally used feature weighting method. Currently, some improved methods based TF-IDF have been proposed, but there is not a method that is able to comprehensive each algorithm´s advantages. So, feature weighting method based on real-coded genetic algorithm (GA) is proposed in this paper, the real-coded GA is used to calculate the feature weights. Concrete steps as follows: firstly, use information gain to reduce dimension. Secondly, use real-coded GA to calculate each feature weights. Lastly, classify text according to the weighted cosine distance. Experiments proved that the real-coded GA method is superior to the traditional TF-IDF method.