Fairness in Proprietary Image Tagging Algorithms: A Cross-Platform Audit on People Images
Open accessThe DOI matches its Crossref record; 14 of the 14 references it cites were found in a registry or an index.
Abstract
There are increasing expectations that algorithms should behave in a manner that is socially just. We consider the case of image tagging APIs and their interpretations of people images. Image taggers have become indispensable in our information ecosystem, facilitating new modes of visual communication and sharing. Recently, they have become widely available as Cognitive Services. But while tagging APIs offer developers an inexpensive and convenient means to add functionality to their creations, most are opaque and proprietary. Through a cross-platform comparison of six taggers, we show that behaviors differ significantly. While some offer more interpretation on images, they may exhibit less fairness toward the depicted persons, by misuse of gender-related tags and/or making judgments on a person’s physical appearance. We also discuss the difficulties of studying fairness in situations where algorithmic systems cannot be benchmarked against a ground truth.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
ImageNet classification with deep convolutional neural networks
Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2017) · Communications of the ACM · doi:10.1145/3065386 · Cited by 112,155
How the machine “thinks”: Understanding opacity in machine learning algorithms
Burrell, J. (2016) · Big Data & Society · doi:10.1177/2053951715622512 · Cited by 3,196 · cited 2×
“However, CogS exhibit common barriers to transparency (Burrell 2016).”
BackgroundCertifying and Removing Disparate Impact
Feldman, M., Friedler, S. A., Moeller, J., Scheidegger, C., & Venkatasubramanian, S. (2015) · Proceedings of the 21th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining · doi:10.1145/2783258.2783311 · Cited by 1,827
The Chicago face database: a free stimulus set of faces and norming data
Ma, D. S., Correll, J., & Wittenbrink, B. (2015) · Behavior Research Methods · doi:10.3758/s13428-014-0532-5 · Cited by 1,788
Gillespie, T. (2014) · Media Technologies · doi:10.7551/mitpress/9042.003.0013 · Cited by 1,016
Men Also Like Shopping: Reducing Gender Bias Amplification using Corpus-level Constraints
Zhao, J., Wang, T., Yatskar, M., Ordonez, V., & Chang, K.-W. (2017) · Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing · doi:10.18653/v1/d17-1323 · Cited by 829 · cited 2×
“Zhao and colleagues (Zhao et al. 2017) found that certain activity labels (e.”
BackgroundDiscrimination in online ad delivery
Sweeney, L. (2013) · Communications of the ACM · doi:10.1145/2447976.2447990 · Cited by 783 · cited 1×
“For example, in a test for racial bias in Google AdSense, Sweeney (Sweeney 2013) conducted Web searches on names, manipulating them by their racial associations.”
MethodAccountability in algorithmic decision making
Diakopoulos, N. (2016) · Communications of the ACM · doi:10.1145/2844110 · Cited by 763
Chua, T. H. H., & Chang, L. (2016) · Computers in Human Behavior · doi:10.1016/j.chb.2015.09.011 · Cited by 704 · cited 1×
“In fact, some findings suggest that social media spaces are projections of one’s idealized self (Chua and Chang 2016) and that the practice of uploading “selfies” can contribute to a feeling of selfworthiness (Stefanone, Lackaff, and Rosen 2011).”
BackgroundFairness in Machine Learning: Lessons from Political Philosophy
Binns, R. (2017) · arXiv · doi:10.48550/arxiv.1712.03586 · Cited by 676
Face Recognition Performance: Role of Demographic Information
Klare, B. F., Burge, M. J., Klontz, J. C., Vorder Bruegge, R. W., & Jain, A. K. (2012) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2012.2214212 · Cited by 516 · cited 1×
“With respect to face recognition in images, Klare and colleagues (Klare et al. 2012) found that particular demographic groups (people of color, women, and younger people aged 18 to 30) were more prone to recognition errors than others.”
BackgroundUnequal Representation and Gender Stereotypes in Image Search Results for Occupations
Kay, M., Matuszek, C., & Munson, S. A. (2015) · Proceedings of the 33rd Annual ACM Conference on Human Factors in Computing Systems · doi:10.1145/2702123.2702520 · Cited by 509 · cited 1×
“Kay and colleagues (Kay, Matuszek, and Munson 2015) demonstrated the use of offline labor statistics as a baseline, in order to measure gender bias in image search engines, in terms of their representations of the professions.”
BackgroundContingencies of Self-Worth and Social-Networking-Site Behavior
Stefanone, M. A., Lackaff, D., & Rosen, D. (2011) · Cyberpsychology, Behavior, and Social Networking · doi:10.1089/cyber.2010.0049 · Cited by 202 · cited 1×
“In fact, some findings suggest that social media spaces are projections of one’s idealized self (Chua and Chang 2016) and that the practice of uploading “selfies” can contribute to a feeling of selfworthiness (Stefanone, Lackaff, and Rosen 2011).”
BackgroundAccountability in Algorithmic Decision-making: A view from computational journalism
Diakopoulos, N. (2015) · Queue · doi:10.1145/2857274.2886105 · Cited by 81
Cited by
Measuring Representational Harms in Image Captioning
Wang, A., Barocas, S., Laird, K., & Wallach, H. (2022) · 2022 ACM Conference on Fairness Accountability and Transparency · doi:10.1145/3531146.3533099 · Cited by 40
“2; the remaining two are presented in the supplementary material as similar techniques have been used previously in other contexts [1, 2, 9, 9, 39, 51, 73].”
MethodComputer Vision and Conflicting Values: Describing People with Automated Alt Text
Hanley, M., Barocas, S., Levy, K., Azenkot, S., & Nissenbaum, H. (2021) · Proceedings of the 2021 AAAI/ACM Conference on AI, Ethics, and Society · doi:10.1145/3461702.3462620 · Cited by 38
Taxonomizing and Measuring Representational Harms: A Look at Image Tagging
Katzman, J., Wang, A., Scheuerman, M., Blodgett, S. L., Laird, K., Wallach, H., & Barocas, S. (2023) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v37i12.26670 · Cited by 32
Metadata
- Authors
- Kyriakou, K., Barlas, P., Kleanthous, S., & Otterbacher, J.
- Venue
- Proceedings of the International AAAI Conference on Web and Social Media
- Published
- 2019-07-06
- Volume
- 13
- Pages
- 313-322
- ISSN
- 2162-3449 (ISSN-L)
- 2334-0770
- OpenAlex
- W2954112064
- Cited by
- 39
- References
- 14
- FWCI
- 7.37
- Type
- conference paper
- Language
- en
- Open access
- diamond
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.