M
Michael S. Bernstein
Researcher at Stanford University
Publications - 207
Citations - 59397
Michael S. Bernstein is an academic researcher from Stanford University. The author has contributed to research in topics: Crowdsourcing & Computer science. The author has an hindex of 52, co-authored 191 publications receiving 42744 citations. Previous affiliations of Michael S. Bernstein include Association for Computing Machinery & Massachusetts Institute of Technology.
Papers
More filters
Proceedings ArticleDOI
Mechanical Novel: Crowdsourcing Complex Work through Reflection and Revision
TL;DR: This paper proposed a technique for achieving interdependent complex goals with crowds, where the crowd loops between reflection, to select a high-level goal and revision, to decompose that goal into low-level, actionable tasks.
Proceedings ArticleDOI
Anyone Can Become a Troll: Causes of Trolling Behavior in Online Discussions
TL;DR: A predictive model of trolling behavior reveals that mood and discussion context together can explain trolling behavior better than an individual's history of trolling, and suggests that ordinary people can, under the right circumstances, behave like trolls.
Proceedings ArticleDOI
Collabio: a game for annotating people within social networks
TL;DR: Collabio's approach of incentivizing members of the social network to generate information about each other produces personalizing information about its users.
Proceedings ArticleDOI
Measuring Crowdsourcing Effort with Error-Time Curves
TL;DR: This work proposes a data-driven effort metric, ETA (error-time area), that can be used to determine a task's fair price and validate the ETA metric on ten common crowdsourcing tasks, finding that ETA closely tracks how workers would rank these tasks by effort.
Posted Content
Scene Graph Prediction with Limited Labels.
TL;DR: This paper introduces a semi-supervised method that assigns probabilistic relationship labels to a large number of unlabeled images using few labeled examples and defines a complexity metric for relationships that serves as an indicator for conditions under which the method succeeds over transfer learning, the de-facto approach for training with limited labels.