I am a PhD candidate at University of Michigan. My research aims to leverage human computation and machine intelligence to effectively solve complex tasks that require domain expertise, such as software development. I study problems that users face during collaboration with existing tools and methods, and build computational systems to assist users via efficient collaboration and hybrid crowd-machine workflow. My advisor is Dr. Steve Oney.
Bashon introduces a crowdsourcing approach to help make program synthesis systems more robust, reliable, and trustworthy, and reduces the cost of downstream data collection for training a program synthesis system.
EdCode applies a semi-asychronous on-demand help seeking model in a learning setting, aiming towards provide more personalized support at scale.
Sifter improves the video curation process by combining automated techniques with a human-powered two-stage pipeline that browses, selects, and reaches an agreement.
Two techniques, interactive event-flow graphs and GUI-level guidance, that guide GUI testers to discover more test cases and avoid duplicate test cases.
Two studies that present the opportunities and the design recommendations of on-demand remote support systems for developers.
Other Peer-Reviewed Publications