Crowdsourcing Without a Crowd: Reliable Online Species Identification Using Bayesian Models to Minimize Crowd Size
- Submitting institution
-
The Open University
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 1461143
- Type
- D - Journal article
- DOI
-
10.1145/2776896
- Title of journal
- ACM Transactions on Intelligent Systems and Technology
- Article number
- 45
- First page
- -
- Volume
- 7
- Issue
- 4
- ISSN
- 2157-6904
- Open access status
- Out of scope for open access requirements
- Month of publication
- May
- Year of publication
- 2016
- URL
-
-
- Supplementary information
-
-
- Request cross-referral to
- -
- Output has been delayed by COVID-19
- No
- COVID-19 affected output statement
- -
- Forensic science
- No
- Criminology
- No
- Interdisciplinary
- No
- Number of additional authors
-
7
- Research group(s)
-
-
- Citation count
- 14
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- This paper develops Bayesian consensus models that minimise crowd size when verifying citizen science data, vital when expertise is limited. It was developed for BeeWatch, the biological recording program we launched with the Bumblebee Conservation Trust to help conserve this vital pollinator group. Over 27000 photo identifications have been crowdsourced. Beewatch featured in RCUK's impact report "Celebrating Success in the Digital Economy" and in the UK Government's National Pollinator Strategy Implementation Plan. This work led to an EPSRC grant on human-AI collaboration (EP/S027513/1). The Royal Horticultural Society uses our data to inform their pollinator-friendly plant lists (details on request).
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -