Monday, February 22, 2016
209 Computer Studies Building
University of Washington
Adaptive Crowd Algorithms for Open-Ended Problems
Although computers are powerful, people have open-ended problem solving skills that computers do not yet have. The challenge is to leverage people's conceptual understanding and rich world knowledge to solve problems that are big, hard, ill-defined and require creativity. I introduce crowd algorithms that can coordinate people's knowledge to solve these problems. Traditional algorithms tend to be rigid and highly parameterized. But to solve open-ended problems, crowd algorithms must adapt to the context of the problem. I introduce four mechanisms to make crowd algorithms adaptive. Adaptive Crowd Algorithms can solve open-ended problems like synthesizing disorganized information into taxonomies, creating conference programs, as well as creative problems such as writing humor.
Bio: Lydia Chilton is a graduate student in Human-Computer Interaction at the University of Washington working with James Landay and Dan Weld. She is currently a visiting student at Stanford University. Her foundational work in crowd algorithms began as an undergraduate and MEng student at MIT. She was awarded a Facebook Fellowship for her work on crowdsourced taxonomy creation, and was awarded a 1-year Brown Institute Grant to continue her work on crowdsourcing humor and other creative artifacts. She likes Star Trek to a degree that embarrasses at least one of her advisors.