Kevin Crowston

Humans, Machines, and the Future of Citizen Science

Date: November 4, 2016

Time: 2:00pm – 3:00pm

Room: Wells Library, Rm LI 030

Abstract:

Gravity Spy is combining humans and machines to support the work of a new kind of citizen science. The program is being developed to support the Laser Interferometer Gravitational Observatory (LIGO), a system which has enough sensitivity to detect astrophysical signals but is also susceptible to terrestrial disturbances known as “glitches.” The Gravity Spy program classifies glitches to remove them from the data and to identify new classes of glitches with causes that can be fixed to eliminate them.

Gravity Spy advances citizen science system design by applying machine learning techniques to work in conjunction with volunteers. Most applications of machine learning to image aim at automation (ie., using human classified data to train algorithms to replace the humans). Gravity Spy explores the reverse relationship, using machine learning to train volunteers by providing them with exemplary images of glitches, which teaches those volunteer to learn to identify those classes. Volunteers progress through several rounds of training, eventually learning to identify new classes of images rather than simply applying the classification provided by the science team.

 

Biography:

Kevin Crowston is a Distinguished Professor of Information Science at the Syracuse University School of Information Studies. He received his A.B. (1984) in Applied Mathematics (Computer Science) from Harvard University and a Ph.D. (1991) in Information Technologies from the Sloan School of Management, Massachusetts Institute of Technology.

His research examines new ways of organizing made possible by the use of information technology. He approaches this issue in several ways: empirical studies of coordination-intensive processes in human organizations (especially virtual organization); theoretical characterizations of coordination problems and alternative methods for managing them; and design and empirical evaluation of systems to support people working together.

He is a co-PI on a recently awarded NSF INSPIRE project: “INSPIRE: Teaming Citizen Science with Machine Learning to Deepen LIGO’s View of the Cosmos” (15-47880). He is the former PI on 2 other NSF-sponsored projects: NSF SOCS Grant 11-11107 for “SOCS: Socially intelligent computing for coding of qualitative data”; and NSF SOCS Grant 12-11071 for “Collaborative Research: Focusing Attention to Improve the Performance of Citizen Science Systems: Beautiful Images and Perceptive Observers”. He and Jian Qin recently were awarded a research challenge grant from ICPSR for the development and dissemination of a capability maturity model for research data management.