Annotators with Attitudes: How Annotator Beliefs And Identities Bias Toxic Language Detection
Open accessThe DOI matches its Crossref record; 20 of the 20 references it cites were found in a registry or an index.
Abstract
Maarten Sap, Swabha Swayamdipta, Laura Vianna, Xuhui Zhou, Yejin Choi, Noah Smith. Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. 2022.
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
The Impact of Social Media on Children, Adolescents, and Families
O'Keeffe, G. S., Clarke-Pearson, K., & Council on Communications and Media (2011) · Pediatrics · doi:10.1542/peds.2011-0054 · Cited by 1,987 · cited 1×
“This can be especially important given that hateful content very often targets marginalized groups and racial minorities (Silva et al., 2016; Sap et al., 2020), and can catalyze violence against them (O’Keeffe et al., 2011; Cleland, 2014).”
BackgroundLanguage (Technology) is Power: A Critical Survey of “Bias” in NLP
Blodgett, S. L., Barocas, S., Daumé III, H., & Wallach, H. (2020) · Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics · doi:10.18653/v1/2020.acl-main.485 · Cited by 1,050 · cited 4×
“…to denote both simple skews or variation in annotations (e.g., for variation in detecting vulgar content as toxic) or representational harms (e.g., AAE being over-detected as toxic or anti-Black content being underdetected as toxic; Barocas et al., 2017; Blodgett et al., 2020). ar X iv :2 11 1.”
BackgroundInfluentialHuff, C., & Tingley, D. (2015) · Research & Politics · doi:10.1177/2053168015604648 · Cited by 903
Genetic and environmental influences on human psychological differences
Bouchard, T. J., & McGue, M. (2003) · Journal of Neurobiology · doi:10.1002/neu.10160 · Cited by 870
The Risk of Racial Bias in Hate Speech Detection
Sap, M., Card, D., Gabriel, S., Choi, Y., & Smith, N. A. (2019) · Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics · doi:10.18653/v1/p19-1163 · Cited by 817
Self-citationAlgorithmic injustice: A relational ethics approach
Birhane, A. (2021) · Patterns · doi:10.1016/j.patter.2021.100205 · Cited by 707
Ex Machina: Personal Attacks Seen at Scale
Wulczyn, E., Thain, N., & Dixon, L. (2017) · Proceedings of the 26th International Conference on World Wide Web · doi:10.1145/3038912.3052591 · Cited by 636
Averaging correlation coefficients: Should Fisher’s z transformation be used?
Silver, N. C., & Dunlap, W. P. (1987) · Journal of Applied Psychology · doi:10.1037/0021-9010.72.1.146 · Cited by 606
Racial Bias in Hate Speech and Abusive Language Detection Datasets
Davidson, T., Bhattacharya, D., & Weber, I. (2019) · Proceedings of the Third Workshop on Abusive Language Online · doi:10.18653/v1/w19-3504 · Cited by 414
Exposure to hate speech increases prejudice through desensitization
Soral, W., Bilewicz, M., & Winiewski, M. (2018) · Aggressive Behavior · doi:10.1002/ab.21737 · Cited by 320
Cited by
Auditing large language models: a three-layered approach
Mökander, J., Schuett, J., Kirk, H. R., & Floridi, L. (2024) · AI and Ethics · doi:10.1007/s43681-023-00289-2 · Cited by 289
ToxiGen: A Large-Scale Machine-Generated Dataset for Adversarial and Implicit Hate Speech Detection
Hartvigsen, T., Gabriel, S., Palangi, H., Sap, M., Ray, D., & Kamar, E. (2022) · Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · doi:10.18653/v1/2022.acl-long.234 · Cited by 279
Self-citationFeng, S., Park, C. Y., Liu, Y., & Tsvetkov, Y. (2023) · Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · doi:10.18653/v1/2023.acl-long.656 · Cited by 149
Li, Z., Zhu, H., Lu, Z., & Yin, M. (2023) · Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing · doi:10.18653/v1/2023.emnlp-main.647 · Cited by 139
The “Problem” of Human Label Variation: On Ground Truth in Data, Modeling and Evaluation
Plank, B. (2022) · Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing · doi:10.18653/v1/2022.emnlp-main.731 · Cited by 121
Metadata
- Authors
- Sap, M., Swayamdipta, S., Vianna, L., Zhou, X., Choi, Y., & Smith, N.
- Venue
- Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies
- Published
- 2022
- Pages
- 5884-5906
- OpenAlex
- W3212327893
- Cited by
- 156
- References
- 20
- FWCI
- 20.52
- 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
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: Annotators with Attitudes: How Annotator Beliefs And Identities Bias Toxic Language Detection. https://app.cochat.ai/papers/10.18653/v1/2022.naacl-main.431
- The paper
- Sap, M., Swayamdipta, S., Vianna, L., Zhou, X., Choi, Y., & Smith, N. (2022). Annotators with Attitudes: How Annotator Beliefs And Identities Bias Toxic Language Detection. Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. https://doi.org/10.18653/v1/2022.naacl-main.431
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.