My research spans HCI, accessibility, crowdsourcing, human computation, artificial intelligence, social computing, computer vision, machine learning, and language technologies.
Currently, I am focused on four broad projects:
- Transitioning crowd-powered systems to automation. I’m working on integrating speech and language technology into Chorus; automatic speech recognition into Scribe; and, automatic computer vision into VizWiz and Zensors.
- Creating a more accessible Web with WebAnywhere, and by crowdsourcing accessibility improvements to existing web content.
- Working to understand dyslexia using human-computer interaction measures, creating tools that help people with dyslexia read and write better, and eventually building tools to diagnose dyslexia earlier and easier.
- Creating a brighter future for crowd workers through education and training. I’m working to design tasks that leverage the expertise that crowd workers already have, and tasks that allow workers to build useful skills while they work.