Microsoft Researching Bing Page Hunt Search Game


Microsoft’s new search engine, Bing, could be improved at some point through the use of an online game called Page Hunt, researchers with Microsoft Research demonstrated in a new paper

Microsoft’s new search engine, Bing, could be improved by playing an online game.

The game, named Page Hunt, presents users with a random Web page, and then asks them to input the search terms that will put that page within a search engine’s top five search results. Depending on how close to the top of the rankings their queries put the Web page, players are awarded points. In order to sweeten the experience, the game adds animations, a top-score list, bonus points, and other “game-like” features.

Page Hunt can be found on this site. It requires Silverlight to run. For the moment, however, it exists entirely as a research project, with no direct connection to Bing.

“One of the nice things about Microsoft is that engineers frequently spend time with Microsoft Research and collaborate on a number of fronts, which often leads to changes in search,” a Microsoft spokesperson noted in an email to eWeek.

As a single-player game, Page Hunt boasts a simplicity that makes even straightforward shoot ‘em ups such as Gears of War look like championship chess. However, the results it generates could contribute mightily to the extraordinarily complex task of refining the search-engine process: an important task for Microsoft as it seeks any possible advantage over Google and Yahoo in the online search space.

The thinking behind the game is described in a research paper, “Page Hunt: Improving Search Engines Using Human Computation Games,” issued by Raman Chandrasekar and Chris Quirk of Microsoft Research, with Abhishek Gupta of Digital Media LLC and Hao Ma of the Chinese University of Hong Kong listed as co-authors.

“We suggest using human computation games to elicit data from players that can be used to improve search,” the abstract of the paper reads. “The data elicited using Page Hunt has several applications including providing metadata for pages, providing query alterations for use in query refinement, and identifying ranking issues.

The original pilot experiment conducted by Chandrasekar and company involved 341 Microsoft employees playing Page Hunt over a 10-day period, generating 14,400 labels for the 744 Web pages in the system. The researchers then “extracted the queries that corresponded to winning trials, generated all pairs of queries as bitext data, and applied the bitext matching algorithm.”

Presumably, Microsoft could use that generated data to fine-tune the algorithm governing Bing, should they decide that the model could contribute to improving the search engine.

Bing remains in third in the U.S. search engine market, with 8.4 percent, behind Google and Yahoo with 65 percent and 19.6 percent, respectively. Microsoft is backing the search engine, which launched on June 3, with a massive ad campaign estimated at costing somewhere in the range of $80 million (£48m) to $100 million.

In its first six weeks, according to a report by research company SearchIgnite, Microsoft’s percentage of the U.S. paid search advertising market stayed flat for the second quarter of 2009, at just below 6 percent. This number corresponds roughly with Microsoft’s tally before the launch of Bing

“Microsoft appears to be focusing its efforts on driving consumer interest and capturing increased search query share,” Roger Barnette, president of SearchIgnite, said in a July 14 statement accompanying the report. “We have not yet seen this translate into more paid search advertising dollars for Microsoft, although typically consumer adoption precedes advertiser adoption.”