Handling uncertainty in citizen science data: towards an improved amateur-based large-scale classification

Jim�nez, Manuel; Triguero, Isaac; John, Robert

Abstract

© 2018 Citizen Science, traditionally known as the engagement of amateur participants in research, is showing great potential for large-scale processing of data. In areas such as astronomy, biology, or geo-sciences, where emerging technologies generate huge volumes of data, Citizen Science projects enable image classification at a rate not possible to accomplish by experts alone. However, this approach entails the spread of biases and uncertainty in the results, since participants involved are typically non-experts in the problem and hold variable skills. Consequently, the research community tends not to trust Citizen Science outcomes, claiming a generalised lack of accuracy and validation. We introduce a novel multi-stage approach to handle uncertainty within data labelled by amateurs in Citizen Science projects. Firstly, our method proposes a set of transformations that leverage the uncertainty in amateur classifications. Then, a hybridisation strategy provides the best aggregation of the transformed data for improving the quality and confidence in the results. As a case study, we consider the Galaxy Zoo, a project pursuing the labelling of galaxy images. A limited set of expert classifications allow us to validate the experiments, confirming that our approach is able to greatly boost accuracy and classify more images with respect to the state-of-art.

Citation

Jiménez, M., Triguero, I., & John, R. (2019). Handling uncertainty in citizen science data: towards an improved amateur-based large-scale classification. Information Sciences, 479, 301-320. https://doi.org/10.1016/j.ins.2018.12.011

• Journal Article Type: Article
• Acceptance Date: Dec 6, 2018
• Online Publication Date: Dec 7, 2018
• Publication Date: Apr 1, 2019
• Deposit Date: Dec 10, 2018
• Publicly Available Date: Dec 10, 2018
• Journal: Information Sciences
• Print ISSN: 0020-0255
• Electronic ISSN: 1872-6291
• Publisher: Elsevier
• Peer Reviewed: Peer Reviewed
• Volume: 479
• Pages: 301-320
• DOI: https://doi.org/10.1016/j.ins.2018.12.011
• Keywords: Control and Systems Engineering; Theoretical Computer Science; Software; Information Systems and Management; Artificial Intelligence; Computer Science Applications
• Public URL: https://nottingham-repository.worktribe.com/output/1395082
• Publisher URL: https://www.sciencedirect.com/science/article/pii/S0020025518309538#ack0001
• Contract Date: Dec 10, 2018