In recent years there has been a massive growth in textual information in textual information especially in the internet. People now tend to read more e-books than hard copies of the books. While searching for some topic especially some new topic in the internet it will be easier if someone knows the pre-requisites and post- requisites of that topic. It will be easier for someone searching a new topic. Often the topics are found without any proper title and it becomes difficult later on to find which document was for which topic. A text categorization method can provide solution to this problem. In this paper domain based ontology is created so that users can relate to different topics of a domain and an automated text categorization technique is proposed that will categorize the uncategorized documents. The proposed idea is based on Term Frequency – Inverse Document Frequency (tf -idf) method and a dependency graph is also provided in the domain based ontology so that the users can visualize the relations among the terms.

Vides a proper solution to this limitation. There are broadly three main categories of Vector Space Model: term-document, word-content and pair-pattern matrices. The main aim of this paper is to discuss broadly the three main categories of VSM for semantic analysis of texts and make proper selection for automatic categorizing. The scenario taken up here is categorization of research papers for organizing a national or an international conference based on the proposed methodology. Computers do not understand human language and this makes it difficult when human wants the computer to do some specific task like categorization according to human need. Vector Space Model (VSM) for semantic analysis of texts and make proper selection of one of the three main categories for automatic categorizing of research papers for organizing a national or an international conference based on the proposed methodology.