Overview
Page Hunt is an online human‑computation game created by Microsoft’s Bing search engine to study and improve human research behavior. Classified as a “game with a purpose,” it combines entertainment with the collection of data useful for refining search‑engine algorithms. The concept of games with a purpose was originally coined by Luis von Ahn, known for CAPTCHA and the ESP Game【1†L1-L5】.
Development and Platform
The game was released as a web application requiring Microsoft Internet Explorer and the Adobe Silverlight plug‑in. Unlike many of von Ahn’s earlier games, Page Hunt is single‑player and does not require user registration or maintain leaderboards【1†L9-L13】.
Gameplay Mechanics
During a three‑minute session, a player is presented with a randomly selected webpage. The objective is to formulate the most effective keyword or phrase that would cause the displayed page to appear within the top five Bing search results for that query. Points are awarded based on the rank achieved (higher rank yields more points), with additional bonuses for finding the page using fewer queries【1†L14-L18】.
Scientific Results and Applications
Data collected from Page Hunt has been employed for several research purposes, including:
- Generating metadata for web pages.
- Deriving query alterations useful for query‑refinement tools.
- Identifying ranking issues within search results.
An internal study reported that approximately 27 % of the pages in the test database were “100 % findable,” meaning every participant could successfully bring those pages into the top five results. Conversely, about 26 % of pages were never found by any player. The study also observed a correlation between URL length and difficulty of “hunting” a page—the longer the URL, the lower the findability. Queries submitted by players were categorized into spelling/punctuation changes, site‑specific alterations, acronym expansions, and conceptual modifications【1†L20-L28】.
Related Human‑Computation Games
Page Hunt belongs to the broader class of human‑computation games, which includes:
- Google Image Labeler
- ESP Game
- Foldit
These games similarly leverage voluntary human effort to solve problems that are challenging for computers alone【1†L30-L33】.
References
- von Ahn, L. “Games with a purpose.” Computer, vol. 29, no. 6, 2006, pp. 92–94.
- Ma, H.; Chandrasekar, R.; Quirk, C.; Gupta, A. “Page Hunt: Improving search engines using human computation games.” Proceedings of the 32nd International ACM SIGIR Conference on Research and Development in Information Retrieval, 2009.
Note: The information presented is based on publicly available sources, primarily the Wikipedia entry for Page Hunt.