Micorsoft’s Online Game Could Boost Bing
By Partho, Gaea News NetworkTuesday, July 28, 2009
Researchers with Microsoft Research have demonstrated in a paper that, Microsoft’s remodeled search engine, Bing could be improved at some point through the use of an online game called Page Hunt. The online game generates data from users that could be used to refine queries and search results. Building on the online game, Microsoft can provide better search results and a more competent search engine for its rivals in the search market Google and Yahoo.
The game called PageHunt offers the users with a random page that asks the users to enter the search term. It would place the web page with search on the top five search results. The players are awarded points depending on how close to the top rankings the queries put the Web page. Page Hunt has been enhanced with cool animations, a top score list, bonus points and other game-like features.
Microsoft’s online game requires silverlight to run. However, its entirely a research project that has no direct connection to Bing. According to a Microsoft spokesperson
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.
About the Game
This is a single player game that’s quite simple and easy making even straightforward moves with Gears of War like chess championship. However, the results generated in the game could contribute mightily to the extraordinary complex task of refining the search engine process. This is an important task for Microsoft as it offers several possible advantage over Google and Yahoo in the online search space.
The idea about the game has been described in a research paper - Page Hunt: Improving Search Engines Using Human Computation Games, which was issued by co-authors 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.
Abstracts of the paper reads,
We suggest using human computation games to elicit data from players that can be used to improve search,
The paper also provides that the data elicited using Page Hunt has several applications that includes providing metadata for pages, providing query alterations for use in query refinement and identifying ranking issues.
Originally, the pilot experiment was conducted by Chandrasekar and company involved 341 Microsoft employees playing Page Hunt over a period of 10 days, which generated over 14,400 labels for the 744 Web pages in the system. The researchers generated all pairs of queries as bitext data and applied the bitext matching algorithm.
Here’s the crux of the story. The generated data in the game can be used by Microsoft to fine-tune the algorithm working behind Bing. This is only possible if the Redmond company thinks that the model could contribute to improving the search engine.
Currently, Microsoft’s Bing remains at third position in market with 8.4 percent, lagging behind Google and Yahoo with 65 percent and 19.6 percent, respectively. Microsoft launched its revamped search engine last month with a massive ad campaign estimated at costing somewhere in the range of $80 million to $100 million.
According to Roger Barnette, president of SearchIgnite,
Microsoft appears to be focusing its efforts on driving consumer interest and capturing increased search query share
He also adds that Microsoft is yet to translate it into a more paid search advertising dollars, although, typically the consumer adoption has preceded the advertiser adoption.
Tags: Bing, Microsoft Research, Online Game, PageHunt, Search Engine