Bias and Fairness in Multimodal Machine Learning: A Case Study of Automated Video Interviews
Open accessThe DOI matches its Crossref record; 9 of the 9 references it cites were found in a registry or an index.
Abstract
We introduce the psychometric concepts of bias and fairness in a multimodal machine learning context assessing individuals’ hireability from prerecorded video interviews. We collected interviews from 733 participants and hireability ratings from a panel of trained annotators in a simulated hiring study, and then trained interpretable machine learning models on verbal, paraverbal, and visual features extracted from the videos to investigate unimodal versus multimodal bias and fairness. Our results demonstrate that, in the absence of any bias mitigation strategy, combining multiple modalities only marginally improves prediction accuracy at the cost of increasing bias and reducing fairness compared to the least biased and most fair unimodal predictor set (verbal). We further show that gender-norming predictors only reduces gender predictability for paraverbal and visual modalities, while removing gender-biased features can achieve gender blindness, minimal bias, and fairness (for all modalities except for visual) at the cost of some prediction accuracy. Overall, the reduced-feature approach using predictors from all modalities achieved the best balance between accuracy, bias, and fairness, with the verbal modality alone performing almost as well. Our analysis highlights how optimizing model prediction accuracy in isolation and in a multimodal context may cause bias, disparate impact, and potential social harm, while a more holistic optimization approach based on accuracy, bias, and fairness can avoid these pitfalls.
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
A guideline of selecting and reporting intraclass correlation coefficients for reliability research
Koo, T. K., & Li, M. Y. (2016) · Journal of Chiropractic Medicine · doi:10.1016/j.jcm.2016.02.012 · Cited by 31,709
A Survey on Bias and Fairness in Machine Learning
Mehrabi, N., Morstatter, F., Saxena, N., Lerman, K., & Galstyan, A. (2019) · arXiv · doi:10.48550/arxiv.1908.09635 · Cited by 5,812
A Survey on Bias and Fairness in Machine Learning
Mehrabi, N., Morstatter, F., Saxena, N., Lerman, K., & Galstyan, A. (2022) · ACM Computing Surveys · doi:10.1145/3457607 · Cited by 5,812
Opensmile: the munich versatile and fast open-source audio feature extractor
Eyben, F., Wöllmer, M., & Schuller, B. (2010) · Proceedings of the 18th ACM international conference on Multimedia · doi:10.1145/1873951.1874246 · Cited by 2,642 · cited 2×
“Paraverbal:TheGenevaMinimalisticAcoustic Parameter Set of features were extracted using OpenSmile [18].”
MethodThe origins of sex differences in human behavior: Evolved dispositions versus social roles.
Eagly, A. H., & Wood, W. (1999) · American Psychologist · doi:10.1037/0003-066x.54.6.408 · Cited by 1,499
Automatic personality assessment through social media language.
Park, G., Schwartz, H. A., Eichstaedt, J. C., Kern, M. L., Kosinski, M., Stillwell, D. J., Ungar, L. H., & Seligman, M. E. P. (2015) · Journal of Personality and Social Psychology · doi:10.1037/pspp0000020 · Cited by 802 · cited 1×
“0 were dropped to remove spurious n-grams (per [41]).”
BackgroundMultimodal Language Processing in Human Communication
Holler, J., & Levinson, S. C. (2019) · Trends in Cognitive Sciences · doi:10.1016/j.tics.2019.05.006 · Cited by 441
50 Years of Test (Un)fairness: Lessons for Machine Learning
Hutchinson, B., & Mitchell, M. (2019) · Proceedings of the Conference on Fairness, Accountability, and Transparency · doi:10.1145/3287560.3287600 · Cited by 297 · cited 4×
“Readersarereferredto[29,36,50]formoreinformationonother biasandfairnessmetrics.”
BackgroundInfluentialKleinberg, J., Ludwig, J., Mullainathan, S., & Rambachan, A. (2018) · AEA Papers and Proceedings · doi:10.1257/pandp.20181018 · Cited by 278
Cited by
Towards a standard for identifying and managing bias in artificial intelligence
Schwartz, R., Vassilev, A., Greene, K., Perine, L., Burt, A., & Hall, P. (2022) · doi:10.6028/nist.sp.1270 · Cited by 548
What is Human-Centered about Human-Centered AI? A Map of the Research Landscape
Capel, T., & Brereton, M. (2023) · Proceedings of the 2023 CHI Conference on Human Factors in Computing Systems · doi:10.1145/3544548.3580959 · Cited by 228
“Work within bias and fairness explores the implications of bias in AI systems and how AI can reinforce societal bias through data and algorithms, with a goal to create AI systems that are fairer and more accurate [40, 258].”
BackgroundFairness and Bias in Algorithmic Hiring: A Multidisciplinary Survey
Fabris, A., Baranowska, N., Dennis, M. J., Graus, D., Hacker, P., Saldivar, J., Zuiderveen Borgesius, F., & Biega, A. J. (2025) · ACM Transactions on Intelligent Systems and Technology · doi:10.1145/3696457 · Cited by 117
A scoping review of fair machine learning techniques when using real-world data
Huang, Y., Guo, J., Chen, W.-H., Lin, H.-Y., Tang, H., Wang, F., Xu, H., & Bian, J. (2024) · Journal of Biomedical Informatics · doi:10.1016/j.jbi.2024.104622 · Cited by 61
Human visual explanations mitigate bias in AI-based assessment of surgeon skills
Kiyasseh, D., Laca, J., Haque, T. F., Otiato, M., Miles, B. J., Wagner, C., Donoho, D. A., Trinh, Q.-D., Anandkumar, A., & Hung, A. J. (2023) · npj Digital Medicine · doi:10.1038/s41746-023-00766-2 · Cited by 53
“The study of bias in video-based AI systems has also gained traction, in the context of automated video interviews 18 , algorithmic hiring 19 , and emotion recognition 20 .”
Background
Metadata
- Authors
- Booth, B. M., Hickman, L., Subburaj, S. K., Tay, L., Woo, S. E., & D'Mello, S. K.
- Venue
- Proceedings of the 2021 International Conference on Multimodal Interaction
- Publisher
- ACM
- Published
- 2021-10-18
- Pages
- 268-277
- OpenAlex
- W3207941483
- Cited by
- 63
- References
- 9
- FWCI
- 9.31
- Type
- conference paper
- Language
- en
- Open access
- hybrid
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.