| | |
Summary: Characterizing Query Intent From
Sponsored Search Clickthrough Data
Azin Ashkan, Charles L.A. Clarke
University of Waterloo, Canada
{aashkan, claclark}@cs.uwaterloo.ca
Eugene Agichtein, Qi Guo
Emory University, United States
{eugene, qguo3}@mathcs.emory.edu
ABSTRACT
Understanding the intention underlying users' queries may
help personalize search results and therefore improve user
satisfaction. If a commercial intent exists, and if an ad is
related to the user's information need, the user may click
on that ad. In this paper, we develop a methodology for
using ad clickthrough logs from a commercial search engine
to study characteristics of commercial intent. The findings
of our study suggest that ad clickthrough features, such as
deliberation time, are effective in detecting query intent. We
also study the effect of query type and the number of dis-
played ads on ad clickthrough behavior.
|
