The existence of abundance information, in combination with the heterogeneous and dynamic nature of the web, makes web exploration a complex process for the average end user. Lower ability of user to precisely express the need and ambiguous queries are the challenging obstacle in improving search results. Retrieved results are sometimes not of user relevance due to keyword based search, so to fill the gap between retrieved result and user interest we need to personalize the results. For example, a biologist and a programmer may use the same query "mouse" with different search context, but the search systems would return same results.. In this paper we proposed an architecture that attempts to identify user search context by analyzing and mapping semantic data using semantic similarity to predict the query topic.
Unfortunately, ACM prohibits us from displaying non-influential references for this paper.
To see the full reference list, please visit http://dl.acm.org/citation.cfm?id=2905270.