• Publications
  • Influence
Instrumenting the crowd: using implicit behavioral measures to predict task performance
TLDR
We present an alternative and complementary technique for evaluating task performance on crowdsourcing markets: examining the way the workers work, rather than the products they produce. Expand
Kinetica: naturalistic multi-touch data visualization
TLDR
We describe an approach for multivariate data visualization that uses physics-based affordances that are easy to intuit and visualize, and a consistent view as data is manipulated in order to promote data exploration and interrogation. Expand
And Now for Something Completely Different: Improving Crowdsourcing Workflows with Micro-Diversions
TLDR
Crowdsourcing has become a popular and indispensable component of many problem-solving pipelines in the research literature, with crowd workers often treated as computational resources that can reliably solve problems that computers have trouble with, such as image labeling/classification. Expand
Estimating the social costs of friendsourcing
TLDR
We introduce an experimental methodology to investigate the perceived social costs of SNS question asking by assigning a monetary value to friendsourcing on Twitter via a monetary choice. Expand
Inserting Micro-Breaks into Crowdsourcing Workflows
TLDR
We propose an initial investigation into possible ways to alleviate worker fatigue and boredom by employing micro-breaks that provide timely relax to workers during long sequences of tasks. Expand
The Effects of Sequence and Delay on Crowd Work
TLDR
A common approach in crowdsourcing is to break large tasks into small microtasks so that they can be parallelized across many crowd workers and so that redundant work can be more easily compared for quality control. Expand
CrowdScape: interactively visualizing user behavior and output
TLDR
We present CrowdScape, a system that supports the human evaluation of complex crowd work through interactive visualization and mixed initiative machine learning, helping users to better understand and harness the crowd. Expand
Environmental chemistry through intelligent atmospheric data analysis
TLDR
We present a new open-source software package designed to facilitate the analysis of atmospheric data, with emphasis on data mining applications applied to single-particle mass spectrometry data from aerosol particles. Expand
Is anyone out there?: unpacking Q&A hashtags on twitter
TLDR
In addition to posting news and status updates, many Twitter users post questions that seek various types of subjective and objective information. Expand
Learning from history: predicting reverted work at the word level in wikipedia
TLDR
We present a machine learning model for predicting whether a contribution will be reverted based on word level features in the edit history of an article. Expand
...
1
2
3
...