Integrating Post-Query Navigation within a Measure

Gabriella Kazai (Microsoft Research)

CSIRO ICT

DATE: 2007-12-03
TIME: 15:00:00 - 16:00:00
LOCATION: CSIT Seminar Room, N101
CONTACT: JavaScript must be enabled to display this email address.

ABSTRACT:
Traditional evaluation of information retrieval (IR) systems is based on implicit assumptions about the users' interaction with the system. It is assumed that the user is presented with a ranked list of results and examines the returned documents one after the other in the order they are listed. In this talk I will argue that such a model is obsolete in the case of the Web and structured document retrieval, where navigation is an integral part of the user's search strategy. I advocate that post-query navigation needs to be reflected in the evaluation framework. I draw on evidence of post-query navigation from user studies and discuss examples of systems that have been developed with the consideration of users' browsing behaviour. In order to capture retrieval effectiveness for query and navigation based search, I introduce a measure of retrieval effectiveness that comprises a probabilistic model of the users' post-query navigation.
BIO:
I am currently working as Associate Researcher at Microsoft Research Cambridge. I am a member of the Integrated Systems team led by Natasa Milic-Frayling. The team develops and integrates new designs and technologies to provide more effective and natural use of computer technology. My research interests include approaches to and evaluation of structured document retrieval, book search and personal digital library systems. Prior to joining Microsoft Research, I conducted my PhD studies at Queen Mary, University of London on the topic of Evaluating XML Information Retrieval. I obtained my MSc from South Bank University and a BEng from Kando College of Technology, Budapest, Hungary.