Problem Statement: The huge number of information on the web as well as thegrowth of new inexperienced users creates new challenges for informationretrieval. It has become increasingly difficult for these users to findrelevant documents that satisfy their individual needs. Certainly the currentsearch engines (such as Google, Bing and Yahoo) offer an efficient way tobrowse the web content. However, the result quality is highly based on usesqueries which need to be more precise to find relevant documents. This taskstill complicated for the majority of inept users who cannot express theirneeds with significant words in the query. For that reason, we believe that areformulation of the initial user's query can be a good alternative to improvethe information selectivity. This study proposes a novel approach and presentsa prototype system called PRESY (Profile-based REformulation SYstem) forinformation retrieval on the web. Approach: It uses an incremental approach tocategorize users by constructing a contextual base. The latter is composed oftwo types of context (static and dynamic) obtained using the users' profiles.The architecture proposed was implemented using .Net environment to performqueries reformulating tests. Results: The experiments gives at the end of thisarticle show that the precision of the returned content is effectivelyimproved. The tests were performed with the most popular searching engine (i.e.Google, Bind and Yahoo) selected in particular for their high selectivity.Among the given results, we found that query reformulation improve the firstthree results by 10.7% and 11.7% of the next seven returned elements. So as wecan see the reformulation of users' initial queries improves the pertinence ofreturned content.
展开▼
