Sarıgil, Erdem2016-01-082016-01-082012http://hdl.handle.net/11693/15684Ankara : The Department of Computer Engineering and the Graduate School of Engineering and Science of Bilkent University, 2012.Thesis (Master's) -- Bilkent University, 2012.Includes bibliographical references leaves 71-77.Nowadays search engines have significant impacts on people’s life with the rapid growth of World Wide Web. There are billions of web pages that include a huge amount of information. Search engines are indispensable tools for finding information on the Web. Despite the continuous efforts to improve the web search quality, a non-negligible fraction of user queries end up with very few or even no matching results in leading commercial web search engines. In this thesis, we provide the first detailed characterization of such queries based on an analysis of a real-life query log. Our experimental setup allows us to characterize the queries with few/no results and compare the mechanisms employed by the three major search engines to handle them. Furthermore, we build machine learning models for the prediction of query suggestion patterns and no-answer queries.xv, 77 leavesEnglishinfo:eu-repo/semantics/openAccessWeb search enginesSearch result qualityQuery difficultyQuery resultsTK5105.884 .S37 2012Search engines--Programming.Web search engines--Mathematical models.Information storage and retrieval systems.Information retrieval.Internet searching.ThesisB133971