Acknowledgments

support, ideas and collaboration that helped immensely in the production this work. The author is also grateful to all the people at the Yahoo! Research Lab in Barcelona, special-ly to Aris Gionis and Carlos Castillo for their contributions to this thesis, and to Debora Donato, Vanessa Murdock, Vassilis Plachouras and Hugo Zaragoza for their valuable ad-vise. The objective of this thesis is to study different applications of Web query mining for the improvement of search engine ranking, Web information retrieval and Web site enhance-ment. The main motivation of this work is to take advantage of the implicit feedback left in the trail of users while navigating through the Web. Throughout this work we seek to demonstrate the value of queries to extract interesting rules, patterns and information about the documents they reach. The models, created in this doctoral work, show that the “wisdom of the crowds ” conveyed in queries has many applications that overall provide a better understanding of users ’ needs in the Web. This allows to improve the general interaction of visitors with Web sites and search engines in a straightforward way