"Communitysourcing: Engaging Local Crowds to Perform Expert Work Via Physical Kiosks"

Online labor markets, such as Amazon’s Mechanical Turk, have been used to crowdsource simple, short tasks like image labeling and transcription. However, expert knowledge is often lacking in such markets, making it impossible to complete certain classes of tasks. In this work we introduce an alternative mechanism for crowdsourcing tasks that require specialized knowledge or skill: communitysourcing — the use of physical kiosks to elicit work from specific populations. We investigate the potential of communitysourcing by designing, implementing and evaluating Umati: the communitysourcing vending machine. Umati allows users to earn credits by performing tasks using a touchscreen attached to the machine. Physical rewards (in this case, snacks) are dispensed through traditional vending mechanics. We evaluated whether communitysourcing can accomplish expert work by using Umati to grade Computer Science exams. We placed Umati in a university Computer Science building, targeting students with grading tasks for snacks. Over one week, 328 unique users (302 of whom were students) completed 7771 tasks (7240 by students). 80% of users had never participated in a crowdsourcing market before. We found that Umati was able to grade exams with 2% higher accuracy (at the same price) or at 33% lower cost (at equivalent accuracy) than traditional single-expert grading. Mechanical Turk workers had no success grading the same exams. These results indicate that communitysourcing can successfully elicit high- quality expert work from specific communities.

I will also spend some time talking about our LocalGround project. LocalGround allows students and community members to use paper maps for collecting local geo-spatial knowledge. Users annotate paper maps using colored markers and symbols. These annotations are automatically extracted and visualized with other data sources and forms of media. Local Ground was used by teenagers from Richmond, California for planning of a public park, and by Oakland youth to document healthy food zones in their communities.

Bio: Tapan Parikh is an Assistant Professor at the School of Information at the University of California, Berkeley. Tapan's research interests include human-computer interaction (HCI), mobile computing, paper and voice UIs and information systems for microfinance, smallholder agriculture, global health and education. For more then 10 years, Tapan has been designing, developing and deploying information systems for communities - initially in India, and now around the world. Tapan and his students have started several technology companies serving community-based organizations (CBOs), non-governmental organizations (NGOs), governments and non-profits. He holds a Sc.B. degree in Molecular Modeling with Honors from Brown University, and M.S. and Ph.D. degrees in Computer Science from the University of Washington, where his dissertation won the William Chan Memorial award. Tapan has also received the NSF CAREER award, was named TR35 Humanitarian of the Year in 2007, and has won best paper awards at several HCI and CS conferences.