Comparative study on using artificial neural networks for text categorization

This paper is a comparative study on using "Artificial Neural Networks" for text categorization problem. In text categorization model using an artificial neural network as a classifier, performance can be an issue if the neural network is trained using the raw feature space since textural data has a very high dimension feature space. Five feature reduction methods were used, including term selection based on document frequency, information gain, mutual information, chi(2)-test, and frequency cut off to observe the behavior of artificial neural networks. The learning machines that were used in the work included "Radial Basis Functions Network" and "Support Vector Machines". The performance of "Naive Bayesian Classifier" was used as a benchmark for the comparative study.