Adventures in Personalized Web Search

Abstract

Even the most conservative estimates of the Web’s current size refer to its billions of documents and daily growth rates that are measured in 10’s of terabytes. To put this into perspective, in 2000 the entire World-Wide Web consisted of about 20 terabytes of information, now it grows by more than 3 times this every single day. This growth frames the information overload problem that is threatening to stall the information revolution as users find it increasingly difficult to locate the right information at the right time in the right way. Even today’s leading search engine technologies are struggling to cope with the sheer quantity of information that is available, a problem that is greatly exacerbated by the apparent inability of Web users to formulate effective search queries that accurately reflect their information needs. This talk will focus on how so-called personalization techniques – which combine ideas from artificial intelligence, user modeling and user interface design – are being used as a practical response to this information overload problem. We will describe the experiences gained, and lessons learned, when it comes to personalizing Web search in the wild, taking special care to consider the issues that are inherent in any approach to personalization in today’s privacy conscious world.