Jill Freyne - Collaborative Web Search: Exploiting Social Interaction Patterns for Increased Result Relevance

Information access systems such as search engines and navigation assistants strive to provide users with access to relevant information given their current needs. Recent research efforts have highlighted the interactive nature of information access behavior and promoted the potential value of harnessing user activity patterns to drive the next generation of social information access tools. The work discussed in this talk revolves around the Collaborative Web Search (CWS) technology developed in University College Dublin. The technology exploits the search interaction patterns of communities of like minded users to provide recommendations of content that reflect the preferences of the community members. CWS is motivated by two key ideas. First, specialized search engines attract communities of users with similar information needs and so serve as a useful way to limit variations in search context. Second, by monitoring user selections for a query it is possible to build a model of query-page relevance based on the probability that a given page will be selected by a user when returned as a result for query. This talk will discuss the implementation and evaluation of CWS in multiple domains as well as an introduction to a spin off technology ASSIST which encompasses a social browsing component to the existing CWS technology.