Implicit user feedback, including click-through and subsequent browsing behavior, is crucial for evaluating and improving the quality of results returned by search engines. Several recent studies [1, 2, 3, 13, 25] have used post-result browsing behavior including the sites visited, the number of clicks, and the dwell time on site in order to improve the ranking of search results. In this paper, we first study user behavior on sponsored search results (i.e., the advertisements displayed by search engines next to the organic results), and compare this behavior to that of organic results. Second, to exploit post-result user behavior for better ranking of sponsored results, we focus on identifying patterns in user behavior and predict expected on-site actions in future instances. In particular, we show how post-result behavior depends on various properties of the queries, advertisement, sites, and users, and build a classifier using properties such as these to predict certain aspects of the user behavior. Additionally, we develop a generative model to mimic trends in observed user activity using a mixture of pareto distributions. We conduct experiments based on billions of real navigation trails collected by a major search engine’s browser toolbar.

Analysis of aggregate Web traffic has shown that PageRank is a poor model of how people actually navigate the Web. Using the empirical traffic patterns generated by a thousand users over the course of two months, we characterize the properties of Web traffic that cannot be reproduced by Markovian models, in which destinations are independent of past decisions. In particular, we show that the diversity of sites visited by individual users is smaller and more broadly distributed than predicted by the PageRank model; that link traffic is more broadly distributed than predicted; and that the time between consecutive visits to the same site by a user is less broadly distributed than predicted. To account for these discrepancies, we introduce a more realistic navigation model in which agents maintain individual lists of bookmarks that are used as teleportation targets. The model can also account for branching, a traffic property caused by browser features such as tabs and the back button. The model reproduces aggregate traffic patterns such as site popularity, while also generating more accurate predictions of diversity, link traffic, and return time distributions. This model for the first time allows us to capture the extreme heterogeneity of aggregate traffic measurements while explaining the more narrowly focused browsing patterns of individual users.

We explore the idea that the Document-Object Model tree of an HTML page — absent any semantic or heuristic interpretations of the tags and their positions — provides cues about the importance of the information it contains. This hypothesis is evaluated by constructing a DomGraph, i.e., a network of the DOM trees of pages connected by their hyperlinks, and using it in a snippet-extraction technique. In this process, we also address technical issues related to the processing of the resultant very large graph. Snippets produced by this technique are compared in a user study to those extracted by a reasonable and simple baseline method, and found to be clearly preferred by users.

NOTICE: This is the author’s version of a work accepted for publication by Elsevier. Changes resulting from the publishing process, including peer review, editing, corrections, structural formatting and other quality control mechanisms, may not be reflected in this document. Changes may have been made to this work since it was submitted for publication. A definitive version was subsequently published in Information Sciences Volume 179, Issue

the characterization of individual users

In presenting this thesis in partial fulfillment of the requirements for a Postgraduate

Many web-based information-seeking tasks are set in a social context where other people’s knowledge and advice improves success in finding information. However, when tightly-knit contacts (friends, family, colleagues) are not available, information seeking becomes more difficult. Inspired by previous work in social navigation, we developed WebWear, a system that collects and displays traces of activity for tightly-knit groups. WebWear allows people to use contextual knowledge of contacts ’ interests and activities to interpret the meaning of the traces, improving their usefulness. In a comparative study, we found that WebWear helped people complete informationseeking tasks more accurately, without requiring additional effort. A one-week field trial found that WebWear was both usable and useful, and that privacy concerns were reduced in the small-group context. WebWear shows that smallscale social navigation systems are feasible, and that they can improve the effectiveness of information seeking on the World-Wide Web.