Ryan Drapeau

Learn More
Crowd workers are human and thus sometimes make mistakes. In order to ensure the highest quality output, requesters often issue redundant jobs with gold test questions and sophisticated aggregation mechanisms based on expectation maximization (EM). While these methods yield accurate results in many cases, they fail on extremely difficult problems with local(More)
The "wisdom of crowds" dictates that aggregate predictions from a large crowd can be surprisingly accurate, rivaling predictions by experts. Crowds, meanwhile, are highly heterogeneous in their expertise. In this work, we study how the heterogeneous uncertainty of a crowd can be directly elicited and harnessed to produce more efficient aggregations from a(More)
We discuss the development of Tactile Graphics with a Voice (TGV), a system used to access label information in tactile graphics using QR codes. Blind students often rely on tactile graphics to access textbook images. Many textbook images have a large number of text labels that need to be made accessible. In order to do so, we propose TGV, which uses QR(More)
A key issue for systems that rely on community contributed, updated, and verified information is motivating and sustain­ ing participation. We investigate this issue in the context of civic, geographically-situated information systems. We fo­ cus on StopInfo, a system that provides detailed information about transit stops, primarily oriented toward blind(More)
  • 1