Basser Seminar Series
Evaluating similarity measures a large-scale study in the Orkut Social Network
Speaker: Associate Professor Ellen Spertus
Mills College, Oakland, California and Google
Time: Wednesday 17 September 2008, 4:00-5:00pm
Location: The University of Sydney, School of IT Building, Lecture Theatre (Room 123), Level 1
Online information services have grown too large for users to navigate without the help of automated tools such as collaborative filtering, which makes recommendations to users based on their collective past behavior. While many similarity measures have been proposed and individually evaluated, they have not been evaluated relative to each other in a large real-world environment. We present an extensive empirical comparison of six distinct measures of similarity for recommending online communities to members of the Orkut social network.
We determine the usefulness of the different recommendations by actually measuring users' propensity to visit and join recommended communities. We also examine how the ordering of recommendations influenced user selection, as well as interesting social issues that arise in recommending communities within a real social network.
Ellen is a research scientist at Google's Mountain View headquarters, where she works on social networks, as well as being an associate professor of computer science at nearby Mills College. She received her bachelor's, master's, and doctoral degrees in computer science from MIT and has done research in computer architecture, Internet search, and online communications and community. She has been active for over 15 years in encouraging girls and women in technology.