A Framework for Query Expansion Based on Viewpoint-Oriented Manipulation of the Related Concepts

Although search engines are quite useful for obtaining information from the World Wide Web, users still have problems obtaining the most relevant information when processing their web queries. Different methods exist for query expansion with various levels of success. A major point in query expansion techniques is to consider the relations existing between the query terms as a means for retrieving more relevant web pages. Therefore, the more comprehensible these relations are observed, the more relevance can be expected for the retrieved web pages. Taking this point into account, in this paper, a framework is represented for query expansion based on viewpoint- oriented manipulation of the related query terms. Comparison between the relevant retrieved documents, on proposed queries with Google results, illustrate how more relevant results are obtained in the situations where the very viewpoints type relations existing between the query terms are clearly detectable and in the meantime no semantic relation may at the first look exists between the query terms. In this paper, we have made use of two approaches to retrieval issue, out of which one is based on information fusion while the other is grounded on collaboration of the results in a selective way.