Contextual and Concept-Based Interactive Query Expansion

In this paper, we present a novel approach for contextual and concept based query formulation in web-based information retrieval, which is an on-going PhD project being undertaken at the Software Engineering Research Lab (SERL) at Auckland University of Technology (AUT). Various query formulation approaches have been studied for a long time with varying degree of success. To the best of our knowledge none of the existing approaches offer a similar service to the one discussed in this paper. Our novel approach centres on the formulation of a high quality search query using a user’s contextual profile, a shared contextual knowledge based, lexical databases and domain-specific concepts. A user’s contextual profile is constructed by monitoring and capturing user’s implicit and explicit data. A shared contextual knowledge based is built by consolidating various users’ contextual profiles. A machine learning technique is employed to learn user’s specific information needs and support the iterative development of a search query by suggesting alternative terms/concepts for query formulation. Early results indicate that the system has the potential to not only aid in the formulation of high quality search queries but also contribute towards the long term goal of intelligent contextual information retrieval from the WWW.