| | |
Summary: Predicting Query Difficulty on the Web by Learning Visual
Clues
Eric C. Jensen, Steven M. Beitzel,
David Grossman, Ophir Frieder
Illinois Institute of Technology Information Retrieval Laboratory
Chicago, IL 60616
{ej,steve,grossman,frieder}@ir.iit.edu
Abdur Chowdhury
Search & Navigation Group
America Online, Inc.
Dulles, VA 20166
cabdur@aol.com
ABSTRACT
We describe a method for predicting query difficulty in a
precision-oriented web search task. Our approach uses visual
features from retrieved surrogate document representations (titles,
snippets, etc.) to predict retrieval effectiveness for a query. By
training a supervised machine learning algorithm with manually
evaluated queries, visual clues indicative of relevance are
discovered. We show that this approach has a moderate
|
