How the accuracy and confidence of sensitivity classification affects digital sensitivity review
- Submitting institution
-
University of Glasgow
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 11-12029
- Type
- D - Journal article
- DOI
-
10.1145/3417334
- Title of journal
- ACM Transactions on Information Systems
- Article number
- 4
- First page
- -
- Volume
- 39
- Issue
- 1
- ISSN
- 1046-8188
- Open access status
- Compliant
- Month of publication
- October
- Year of publication
- 2020
- URL
-
http://eprints.gla.ac.uk/221945/
- 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
-
2
- Research group(s)
-
-
- Citation count
- 0
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- ORIGINALITY: First user study examining how sensitivity classification can increase Government sensitivity reviewers’ speed and accuracy, to comply with FOI laws. RIGOUR: Guidelines developed with FCDO (Foreign Office) expert reviewers. Following best practices for within-subject designs, repeated-measures ANOVAs and ‘Cousineau and Morey’ confidence intervals are used, ensuring robustness and SIGNIFICANCE of results. SIGNIFICANCE: Highly-selective top ranked IR/IS journal. Demonstrates how sensitivity classifiers increase reviewing speed by ~72%, while maintaining high reviewer accuracy, enabling significant efficiency/cost savings. Research funded by and informing and having impact on FCDO Services (UK Government) deployment through Project Cicero.
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -