A Survey on text categorization of Indian and non-Indian languages using supervised learning techniques

Categorization of text plays an important role in the text mining field. Text categorization is the process in which documents are categorized into its predefined category. Automatic text categorization is an important task due to large amount of electronic documents. This paper presents a survey of Text categorization of Indian and non-Indian languages. There is very less work done in text categorization of Indian languages. To extract the features of documents, mostly TF-IDF (Term frequency-Inverse document frequency) method is used. Major classifiers such as SVM (support vector machine), NB (Naïve Bayes), Decision tree and K-NN (K-Nearest neighbor) are used for text categorization process. Measures used to evaluate performance of text categorization are recall, precision and fmeasure. Keywords-Text Categorization, TF-IDF, SVM, NB.