A paper authored by doctoral candidate Peter Organisciak will presented by a coauthor at the International Joint Conference on Artificial Intelligence (IJCAI-15) on July 31. Held in Buenos Aires, Argentina, on July 25-31, IJCAI-15 is sponsored by the IJCAI, a scientific and educational nonprofit, in partnership with the Argentinean Association of Artificial Intelligence and cosponsored by Argentina’s Ministry of Science, Technology and Productive Innovation; the Department of Computer Science at the School of Exact and Natural Sciences of Buenos Aires University; and the Department of Computer Science and Engineering at Universidad Nacional del Sur.
Organisciak and coauthors Jaime Teevan, Susan Dumais, Robert C. Miller, and Adam Tauman Kalai were invited to present their paper, “Matching and Grokking: Approaches to Personalized Crowdsourcing,” which is adapted from work presented previously at the Second AAAI Conference on Human Computation and Crowdsourcing (HCOMP) in November 2014. The group was recognized with the notable paper award at HCOMP 2014.
Abstract: Personalization aims to tailor content to a person's individual tastes. As a result, the tasks that benefit from personalization are inherently subjective. Many of the most robust approaches to personalization rely on large sets of other people's preferences. However, existing preference data is not always available. In these cases, we propose leveraging online crowds to provide on-demand personalization. We introduce and evaluate two methods for personalized crowdsourcing: taste-matching for finding crowd workers who are similar to the requester, and taste-grokking, where crowd workers explicitly predict the requester's tastes. Both approaches show improvement over a non-personalized baseline, with taste-grokking performing well in simpler tasks and taste-matching performing well with larger crowds and tasks with latent decision-making variables.
Organisciak’s research interests lie at the intersection of online systems and users, specifically at the juncture between the humanistic view of users and the technical considerations of systems design. At GSLIS, he is working his dissertation titled, “Reliable collection and use of document metadata through crowdsourcing.” He holds master’s degree in humanities computing from the University of Alberta and a bachelor’s degree in communication studies and multimedia from McMaster University. Organisciak has previously received honors for excellence in research and publication, including the 2014 outstanding contribution award from the Canadian Society for Digital Humanities, the best paper award at the annual meeting of the Association for information science and technology in 2011, and the best student paper award at the Society for Digital Humanities conference in 2011. He has twice been selected for the Fortier Prize for young scholars shortlist.