Sign In

Communications of the ACM

ACM TechNews

Let the Search Engine Try Again

View as: Print Mobile App Share:

A Pennsylvania State University researcher has analyzed the way Web surfers reformulate their Web searches and believes his research could lead to improvements in the design of search engines. Professor Jim Jansen studied nearly one million Web searches to uncover patterns in the way users change their search terms. He found that the search terms were changed in 22 percent of queries, but users did not often seek assistance from systems for finding the desired information.

"The implication is that system assistance should be most specifically targeted when the user is making a cognitive shift because it appears users are open to system intervention," he says.

Jansen also created models to predict how people change search terms to offer a more precise query, which could be helpful for designing more advanced search engines.

"Given that one can predict future states of query formulation based on previous and present states with a reasonable degree of accuracy, one can design information systems that provide query reformulation assistance, automated searching assistance systems, recommender systems, and others," he says.

From Penn State Live
View Full Article


Abstracts Copyright © 2009 Information Inc., Bethesda, Maryland, USA


No entries found

Sign In for Full Access
» Forgot Password? » Create an ACM Web Account