

On the heals of being mentioned in Professor Marti Hearst’s new book (see below), we’re thrilled to announce that the Association for Computing Machinery’s Special Interest Group on Information Retrieval has selected Surf Canyon to present at SIGIR 2009. Considered one of the most important conferences in the field of information retrieval, the event will be in Boston from July 19th-23rd. Mark Cramer, CEO, will be presenting the research paper “Demonstration of Improved Search Result Relevancy Using Real-Time Implicit Relevance Feedback” at the workshop “Understanding the user – Logging and interpreting user interactions in information search and retrieval.”
One reviewer had this to say:
“The paper presents an empirical evaluation of an algorithm for improving search results from implicit feedback in web search. The algorithm is proprietary, but nevertheless is the evaluation extremely interesting. Unlike most prior work, the evaluation is done on an operational system with real users, and it gives a lot of insight into the benefits or short term personalization. This is a great paper and one of the most interesting IR papers I have read in a while! This paper by itself would already make me come to the workshop. Very intersting, original, and relevant.”
Marti Hearst, Professor in the School of Information at the University of California, Berkeley, who previously appraised Surf Canyon in a Technology Review article, recently released her new book, Search User Interfaces. In her sweeping review of the state of the art of search interface design, based on both academic research and deployment in commercial systems, Surf Canyon is honored to be mentioned in chapter 9.2.1, “Personalization in Search:”
“The use of implicit information from viewing of documents described in this section makes use of a user’s interaction history over many query sessions. An alternative is to automatically adjust the rankings in real time, during a single search session. Singh et al., 2008 use a version of the clickthrough inversion idea described in Chapter 5 to re-rank the hits returned for a single query and the user views those results. The terms associated with the links that have been clicked on so far are weighted positively, while those not clicked on are weighted negatively, to provide a real-time re-ranking. A similar idea is being promoted by the startup company SurfCanyon…”
Source: SurfCanyon Blog
















