Paper Title
SBM – A Semantic Based Mining Method To Cluster The Content Of The Web

Abstract
Abstract- SBM aims to present a novel ontology-based content-mining approach to cluster research proposals deep web search based on their similarities. The used method is efficient and effective for clustering research proposals with English texts. Text-mining methods have been proposed to solve the problem by automatically classifying text documents. Current search methods for grouping proposals are based on manual matching of similar search discipline keywords. The advantages of this method are that it can extract three types of data records, namely, synonyms data records, hypernymy data records, and hyponyms data records, and also provides options for aligning iterative and disjunctive data items. The proposed SBM is used together with statistical method and optimization models and consists of reference to the ontology; the new proposals in each discipline are clustered using a self-organized mapping (SOM) algorithm. The SOM algorithm is a typical unsupervised learning neural network model that clusters input data with similarities. Our new techniques used in data extraction from deep webs needs to be improved to achieve the efficiency and finally the result is given like the result comes for user query on multi view point like web links, news contents and the synonym hyponym and hypernym for the input term specified.