Microsoft researchers are seeking ways to improve internet search results by looking at how people use and interact with search engines.
Researchers Eugene Agichtein, Eric Brill, Susan Dumais and Robert Ragno argue that accurately modeling and interpreting users’ interactions with the search engines can improve search results, in two papers submitted this year’s Association for Computing Machinery SIGIR (special interest group on information retrieval) conference in Seattle this week.
The Microsoft team says looking at the way users browse through search results can help detect “click-spam”, improve the personalisation of web searches and enhance user experience.
But they argue that robust new techniques to analyse and understand the relationship between user interactions and result quality are needed.
The research to be presented to the SIGIR conference discusses how patterns of user behaviour can be used to improve the algorithms that rank results from web searches.
Researcher Eugene Agichtein said, “By examining click-through and browsing patterns across a large number of users, we are able to learn a great deal about how people interact with search technologies and can
thereby improve our accuracy dramatically.”
Vote for your IT greats
Who have been the most influential people in IT in the past 40 years? The greatest organisations? The best hardware and software technologies? As part of Computer Weekly’s 40th anniversary celebrations, we are asking our readers who and what has really made a difference?
Vote now at: www.computerweekly.com/ITgreats