Web Retrieval: The Role of Users
Web retrieval methods have evolved through three major steps in the last decade or so. They started from standard document-centric IR in the early days of the Web, then made a major step forward by leveraging the structure of the Web, using link analysis techniques in both crawling and ranking challenges. A more recent, no less important but maybe more discrete step forward, has been to enter the user in this equation in two ways: (1) Implicitly, through the analysis of usage data captured by query logs, and session and click information in general; the goal here being to improve ranking as well as to measure user’s happiness and engagement; (2) Explicitly, by offering novel interactive features; the goal here being to better answer users’ needs. This half day tutorial will cover the user-related challenges associated with the implicit and explicit role of users in Web retrieval. More speciﬁcally, we will review and discuss challenges associated with:
- Usage data analysis and metrics - It is critical to monitor how users take advantage and interact with Web retrieval systems, as this implicit relevant feedback aggregated at a large scale, can provide insights on users’ underlying intent as well as approximate quite accurately the level of success of a given feature. Here we have to consider not only clicks statistics, the sequences of queries, the time spent in a page, the number of actions per session, etc. This is the focus of the ﬁrst part of the tutorial.
- User interaction - Given the intrinsic problems posed by the Web, the key challenge for the user is to conceive a good query to be submitted to the search system, one that leads to a manageable and relevant answer. The retrieval system must assist users during two key stages of interaction: before the query is fully expressed and after the results are returned. After quite some stagnation on the front-end of Web retrieval, we have seen numerous novel interactive features appear in the last 3 to 4 years, as the leading commercial search engines seem to compete for users’ attention. The second part of the tutorial will be dedicated to explicit user interaction. We will introduce novel material (as compared to previous versions of this tutorial that were given at SIGIR’2010, WSDM’2011 and ECIR’2011) in order to reﬂect recent Web search features such as Google Instant or Yahoo! Direct Search.
Ricardo Baeza-Yates is VP of Yahoo! Research for Europe and Latin America, Leading the labs at Barcelona, Spain and Santiago, Chile. Until 2005, he was the director of the Center for Web Research at the Department of Computer Science of the Engineering School of the University of Chile, and ICREA Professor at the Dept. of Technology of University Pompeu Fabra in Barcelona, Spain. He is co-author of the book Modern Information Retrieval, whose second edition appeared in 2011, as well as co-author of the second edition of the Handbook of Algorithms and Data Structures, Addison-Wesley, 1991; and co-editor of Information Retrieval: Algorithms and Data Structures, Prentice-Hall, 1992, among more than 200 other publications. He has been PC-Chair of the most important conferences in the ﬁeld of Web Search and Web Mining. Most recently, he was one of the co-chairs WWW2010 Web Search Track and PC-co chair of SIGIR’2011. He has received the organization of American States award for young researchers in exact sciences (1993) and with two Brazilian research article (1997). In 2003 he was the ﬁrst computer scientist to be elected to the Chilean Academy of Sciences. During 2007, he was awarded the Graham Medal for innovation in computing, given by the University of Waterloo to distinguished ex-alumni and in 2009 was named ACM Fellow. He has been giving tutorials in most major conferences many times, including SIGIR, WWW and VLDB.
Yoelle Maarek is the Senior Director of Yahoo! Research in Israel, which she joined in 2009. Before this, she was an Engineering Director at the Google Haifa Engineering Center, which she founded in 2006 and grew to close to 40 staff members. Her team at Google Haifa launched several visible features on Google and YouTube worldwide, such as “Google Suggest”, the query completion feature on google.com, and YouTube Video Annotations. Prior to this, Yoelle had been with IBM Research since 1989. While there, she held a series of technical and management positions ﬁrst at the T.J. Watson Research in New York, USA, and then at the IBM Haifa Research Lab in Israel, at which point she headed the search and collaboration activities and was appointed to Distinguished Engineer. Yoelle graduated from the “Ecole Nationale des Ponts et Chaussees” in Paris, France, and received her DEA (graduate degree) in Computer Science from Paris VI University, both in 1985. She was a visiting PhD student at Columbia University in NY in 1986/87. She received her PhD in Computer Science from Technion, Israel, in 1989. She has published over 50 papers in domains related to information retrieval, Web search and Web applications. She has served as vice-chair for several tracks at WWW, as senior PC member at several ACM SIGIR conferences, and as Senior PC at WSDM’2011. Yoelle has organized several workshops at major conferences in the ﬁeld, and a few tutorials most recently at SIGIR’2010, WSDM’2011 and ECIR’2011. Yoelle was a PC co-chair of WWW’2009 and will serve as PC co-chair at WSDM’2012 and SIGIR’2012. She is on the editorial board of the Information Processing and Management Journal, is a member of the Board of Governors of Technion, Israel Institute of Technology and an ACM distinguished scientist.