A Neoteric Method for the Classification of Text Using SVM Classifier.

Abstract

in today’s world, browsing for exact information has become very tedious job as the number of electronic documents on the Internet has grown big and large. It is necessary to classify the documents into categories so that retrieval of documents becomes easy and more efficient. We try to overcome this difficulty by efficiently organizing, the documents into set of related topics or categories, which enable the user query process, to be precise and optimized. Main goal of this paper is to classify documents into a certain number of predefined categories. We have used k-means clustering algorithm, tf-idf feature extraction for indexing and SVM classifier.