Web documents semantic similarity by extending document ontology using current trends

Semantic evaluation of similarity index is computation of relatedness between terms/concepts/documents. In this paper, we have given a novel semantic similarity approach to overcome the limitations that exists in calculating semantic similarity score. In our approach we are extracting words/terms from the set of documents, and then replacing the extracted words/terms by their respective set of probable concepts stored in a dictionary. The concepts retrieved from the dictionary are connected using relationships from a base ontology for construction of document ontology corresponding to a given document. The ontology constructed this way is further extended using trend relationships stored in a separate database. Finally, the extended documents' ontology is compared for finding the relatedness between the documents. It is proved empirically that the proposed approach gives the better results of semantic similarity as compared with the conventional approaches.