An Efficient Way of Classifying and Clustering Documents Based on SMTP U.Umamaheswari [1] , Mr.G.Shivaji Rao M.E. [2] , M.E scholar, Assistant Professor, [1] Department of Computer Science and Engineering, [2] Department of Computer Science and Engineering, Sree Sowdambika College of Engineering, Sree Sowdambika College of Engineering, Aruppukottai-626 134, Aruppukottai-626 134, Tamil Nadu, Tamil Nadu, India. India. 13umamaheswari@gmail.com shivajirao88@gmail.com Abstract In text processing, the similarity measurement is the important process. It measures the similarities between the two documents. In this project we proposed the new similarity measurement. The computation of similarity measurement is based on the feature of two documents. Our proposed system contains three case to compute the similarity. The three cases are, both two documents contains features, only one document contains feature, there is no feature into the two documents. In first case, the similarity is increased when the differences of feature value is decreased between the two documents. Then the given differences are scaled. In second case, fixed value is given to the similarity. In third cases there is no contribution to the similarity. Finally our proposed measure method achieves the better performance compared than other measurement methods. Index Terms—Document classification, document clustering, entropy, accuracy, classifiers, clustering algorithms I. INTRODUCTION Text processing plays an important role in information retrieval, data mining, and web search. A document is any content drawn up or received by the Foundation concerning a matter relating to the policies, activities and decisions falling within its competence and in the framework of its official tasks, in whatever medium (written on paper or stored in electronic form , including e-mail, or as a sound, visual or audio-visual recording). The term classification means the allocation of an appropriate level of security (as confidential or restricted) to a document the unauthorised disclosure of which might prejudice the interests of the Foundation, the EU or third parties. Documents are confidential when their unauthorised disclosure could harm the essential interests of an individual, the Foundation or the EU. Documents are restricted when their unauthorised disclosure could be Disadvantageous to the Foundation, the EU or a third party. Documents are restricted when their unauthorised disclosure could be disadvantageous to the Foundation, the EU or a third party. The term originator means the duly authorised author of a classified document. The term downgrading means a reduction in the level of classification. The term declassification means the removal of any classification. RULES FOR CLASSIFICATION Foundation documents that are not public shall be classified in one of the following categories: confidential or restricted. Criteria and guidance for classification are set out in Annex 1 to this decision. The classification of a document shall be decided by the originator based on these rules. All classified documents shall be recorded in a register of classified documents. Applications for access to classified documents shall be examined by the Director. If a classified document is to be made available in response to a request from a member of the public, it shall be first declassified by a decision of the Director. Documents shall be classified only when necessary. The classification shall be clearly indicated and shall be maintained only as long as the document requires protection. The classification of a document shall be determined by the level of sensitivity of its contents. Classification of documents shall be periodically reviewed. By request of the Document Management Officer (DMO), the originator of a document shall indicate if that document or information may be downgraded and declassified. Where a document or information is declassified, details shall be recorded in the register and the document shall be archived appropriately. Where classification is retained, details of the review shall be entered Proceedings of International Conference on Developments in Engineering Research ISBN NO : 378 - 26 - 13840 - 9 www.iaetsd.in INTERNATIONAL ASSOCIATION OF ENGINEERING & TECHNOLOGY FOR SKILL DEVELOPMENT 50