An Algorithm to use Feedback on Viewed Documents to Improve Web Query: Enabling naive searchers to search the Web smartly

Abstract

This paper presents an algorithm to improve a web search query based on the feedback on the viewed documents. A user who is searching for information on the Web marks the retrieved (viewed) documents as relevant or irrelevant to further expose the information needs expressed in the original query. A new web search query matching this improved understanding of the user's information needs is synthesized from these text documents. The methodology provides a way for creating web search query that matches the user's information need even when the user may have difficulty in doing so directly due to lack of experience in the query design or lack of familiarity of the search domain. A user survey has shown that the algorithmically formed query has recall coverage and precision characteristics better than those achieved by the experienced human web searchers.