Personalized Semantic Retrieval and Summarization of Web Based Documents

The current retrieval methods are essentially based on the string-matching approach lacking of semantic information and can't understand the user's query intent and interest very well. These methods do regard as the personalization of the users. Semantic retrieval techniques are performed by interpreting the semantic of keywords. Using the text summarization allows a user to get a sense of the content of a full-text, or to know its information content, without reading all sentences within the full-text. In this paper, a semantic personalized information retrieval (IR) system is proposed, oriented to the exploitation of Semantic Web technology and WordNet ontology to support semantic IR capabilities in Web documents. In a proposed system, the Web documents are represented in concept vector model using WordNet. Personalization is used in a proposed system by building user model (UM). Text summarization in a proposed system is based on extracting the most relevant sentences from the original document to form a summary using WordNet. The examination of the proposed system is performed by using three experiments that are based on relevance based evaluation. The results of the experiment shows that the proposed system, which is based on Semantic Web technology, can improve the accuracy and effectiveness for retrieving relevant Web documents.