The DOI matches its Crossref record; 13 of the 13 references it cites were found in a registry or an index.
Reducing Gender Bias in Abusive Language Detection
Open accessAbstract
Abusive language detection models tend to have a problem of being biased toward identity words of a certain group of people because of imbalanced training datasets.For example, "You are a good woman" was considered "sexist" when trained on an existing dataset.Such model bias is an obstacle for models to be robust enough for practical use.In this work, we measure gender biases on models trained with different abusive language datasets, while analyzing the effect of different pre-trained word embeddings and model architectures.We also experiment with three bias mitigation methods: (1) debiased word embeddings, (2) gender swap data augmentation, and (3) fine-tuning with a larger corpus.These methods can effectively reduce gender bias by 90-98% and can be extended to correct model bias in other scenarios.
Overview
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
The cited source says what the claim attributes to it.
In the citing paper
“Prior work has shown that toxicity classifiers can pick up on biases in the training data and spuriously associate toxicity with the mention of certain demographics (Park et al., 2018; Dixon et al., 2018).”
From WILDS: A Benchmark of in-the-Wild Distribution Shifts (2020) · cites this paper as Park et al., 2018
In the citing paper
“models are trained with historical data and can present issues such as gender bias and racial bias in AI models [68,73], potentially exacerbating structural inequalities [10]”
From Human-AI Collaboration via Conditional Delegation: A Case Study of Content Moderation (2022) · cites this paper as [68]
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
Distributed Representations of Words and Phrases and their Compositionality
Mikolov, T., Sutskever, I., Chen, K., Corrado, G., & Dean, J. (2013) · arXiv · doi:10.48550/arxiv.1310.4546 · Cited by 24,533
Enriching Word Vectors with Subword Information
Bojanowski, P., Grave, E., Joulin, A., & Mikolov, T. (2017) · Transactions of the Association for Computational Linguistics · doi:10.1162/tacl_a_00051 · Cited by 9,645
Semantics derived automatically from language corpora contain human-like biases
Caliskan, A., Bryson, J. J., & Narayanan, A. (2017) · Science · doi:10.1126/science.aal4230 · Cited by 2,887
Hateful Symbols or Hateful People? Predictive Features for Hate Speech Detection on Twitter
Talat, Z., & Hovy, D. (2016) · North American Chapter of the Association for Computational Linguistics · doi:10.18653/v1/n16-2013 · Cited by 1,919 · cited 2×
“So far, many efforts were put into defining and constructing abusive language datasets from different sources and labeling them through crowd-sourcing or user moderation (Waseem and Hovy, 2016; Waseem, 2016; Founta et al., 2018; Wulczyn et al., 2017).”
BackgroundDeep Learning for Hate Speech Detection in Tweets
Badjatiya, P., Gupta, S., Gupta, M., & Varma, V. (2017) · International World Wide Web Conference (WWW) · doi:10.1145/3041021.3054223 · Cited by 1,253
Felbo, B., Mislove, A. E., Søgaard, A., Rahwan, I., & Lehmann, S. (2017) · Research at the University of Copenhagen (University of Copenhagen) · Cited by 712
Gender bias in coreference resolution: Evaluation and debiasing methods
Zhao, J., Wang, T., Yatskar, M., Ordonez, V., & Chang, K.-W. (2018) · Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 2 (Short Papers) · doi:10.18653/v1/n18-2003 · Cited by 684 · cited 3×
“This simple method removes correlation between gender and classification decision and has proven to be effective for correcting gender biases in co-reference resolution task (Zhao et al., 2018).”
BackgroundMethodInfluentialMeasuring and Mitigating Unintended Bias in Text Classification
Dixon, L., Li, J., Sorensen, J., Thain, N., & Vasserman, L. (2018) · Proceedings of the 2018 AAAI/ACM Conference on AI, Ethics, and Society · doi:10.1145/3278721.3278729 · Cited by 674 · cited 5×
“Therefore, we generate a separate unbiased test set for each gender, male and female, using the identity term template method proposed in Dixon et al. (2017).”
BackgroundMethodInfluentialEx 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 · cited 1×
“So far, many efforts were put into defining and constructing abusive language datasets from different sources and labeling them through crowd-sourcing or user moderation (Waseem and Hovy, 2016; Waseem, 2016; Founta et al., 2018; Wulczyn et al., 2017).”
BackgroundLarge Scale Crowdsourcing and Characterization of Twitter Abusive Behavior
Founta, A.-M., Djouvas, C., Chatzakou, D., Ilias Leontiadis, A., Blackburn, J., Stringhini, G., Vakali, A. I., Sirivianos, M., & Kourtellis, N. (2018) · Proceedings of the International AAAI Conference on Web and Social Media · doi:10.1609/icwsm.v12i1.14991 · Cited by 605
Research works printed but not linked: 6
- Tolga Bolukbasi, Kai-Wei Chang, James Y Zou, Venkatesh Saligrama, and Adam T Kalai. 2016. Man is to computer programmer as woman is to homemaker? debiasing word embeddings. In Ad- vances in Neural Information Processing Systems, pages 4349-4357.
- Svetlana Kiritchenko and Saif M Mohammad. 2018. Examining gender and race bias in two hundred sen- timent analysis systems. Proceedings of the 7th Joint Conference on Lexical and Computational Se- mantics(*SEM), New Orleans, USA.
- Tomas Mikolov, Ilya Sutskever, Kai Chen, Greg S Cor- rado, and Jeff Dean. 2013. Distributed representa- tions of words and phrases and their compositional- ity. In NIPS, pages 3111-3119.
- Ji Ho Park and Pascale Fung. 2017. One-step and two- step classification for abusive language detection on twitter. ALW1: 1st Workshop on Abusive Language Online to be held at the annual meeting of the Asso- ciation of Computational Linguistics (ACL) 2017.
- Zeerak Waseem. 2016. Are you a racist or am i seeing things? annotator influence on hate speech detection on twitter. In Proceedings of the first workshop on NLP and computational social science, pages 138- 142.
- Brian Hu Zhang, Blake Lemoine, and Margaret Mitchell. 2018. Mitigating unwanted biases with ad- versarial learning. Proceedings of AAAI/ACM Con- ference on Ethics and Society(AIES) 2018.
Cited by
Sorted by citations
Items 301–322 of 322
Inherent Bias in Chatbots: Is It Possible to Create and AI Entity Without Any Bias?
Crowder, J. A. (2023) · Synthesis lectures on engineering, science, and technology · doi:10.1007/978-3-031-45509-4_12
Qin, Y. (2023) · IEEE International Conference on Electrical, Automation and Computer Engineering (ICEACE) · doi:10.1109/iceace60673.2023.10442889
“[19] Talk about how gender stereotypes are represented in the wording used in letters of reference for academic positions and other career evaluations.”
BackgroundBattling cultural bias within hate speech detection: An experimental correlation analysis
Bhattacharya, S., & Kanzinger, J. (2024) · Journal of Emerging Investigators · doi:10.59720/23-156
RETRACTED: Algorithmic Bias: An Integrative Review and Scope for Future ResearchPreprint
Chaudhary, A. (2024) · Research Square · doi:10.21203/rs.3.rs-4775268/v1 · Cited by 3
RetractedDebiasing Large Language Models with Structured Knowledge
Ma, C., Tianyu, Z. H. A. O., & Okumura, M. (2025) · IEICE Transactions on Information and Systems · doi:10.1587/transinf.2024edp7326
AI Surrogacy in Psychological ResearchPreprint
D’Alessandro, W., & Thompson, J. A. F. (2025) · PsyArXiv (OSF Preprints) · doi:10.31234/osf.io/6emg9_v1
Pronoun Matters: A Benchmark for Diagnosing Gender Bias in Emotion Classification
Aisha, Q. U. A., Cho, Y.-J., & Kim, B. G. (2025) · Communications in computer and information science · doi:10.1007/978-981-95-3141-7_9
DMCP: A Novel Debiasing Method Based on Contrastive Learning and Prompt Learning
Liang, H., He, J., Lin, J., Lin, N., Zhou, D. M., & Yang, A. (2025) · IEEE International Conference on Big Data Analytics (ICBDA) · doi:10.1109/icbda65366.2025.11211018
“ED is a standard metric to evaluate fairness and bias of document classifiers [27], [28].”
Park, S., Cho, E., Jung, C. Y., Kang, W. C., Kim, T., Park, E., & Song, S. (2025) · Scientific Data · doi:10.1038/s41597-025-06344-3
“In response to pervasive gender bias across NLP pipelines, prior research has proposed debiasing methods such as data augmentation 16 , fine-tuning 17 , and modifications to word embeddings 18–21 .”
Overview of the NLPCC 2025 Shared Task: Gender Bias Mitigation Challenge
Li, Y., Zhang, G., Hong, H., Wang, Y., & Lin, C. (2025) · Lecture notes in computer science · doi:10.1007/978-981-95-3352-7_38
Li, C., Zhang, J., Zhang, L., & Zheng, Q. (2025) · Lecture notes in computer science · doi:10.1007/978-981-95-3352-7_40
FABLE: Fairness Attack in Abusive Language Detection
Liang, Y., Cheng, L., Payani, A., & Shu, K. (2025) · IEEE International Conference on Big Data (BigData) · doi:10.1109/bigdata66926.2025.11401648
“For instance, studies have examined dialect biases against African American English (AAE) dialects [7], [13], [14] compared to Standard American English (SAE), and biases related to general identity terms such as gender and race [5], [8], [12].”
Detecting and Mitigating Social Bias in Transformer Language Models
Dahatonde, R. T., Rashmi, R., Motghare, M., Shelke, N. M., Ashtankar, N., & Guda, S. (2025) · IEEE Global Conference on Wireless Computing and Networking (GCWCN) · doi:10.1109/gcwcn66157.2025.11448494
Text Generation with and without Retrieval
Fan, H. (2021) · theses.fr (ABES) · doi:10.70675/87ca97d1z017cz478azac26z38a64f0a75e0
Automatic Hate Speech Detection on Social Media
Chiril, P. (2021) · theses.fr (ABES) · doi:10.70675/3d8fbeb4z4be4z46b5z8044zff3688df0033
Expanding the training data for neural network based hate speech classification
d'Sa, A. G. (2022) · theses.fr (ABES) · doi:10.70675/e5736942z9e13z4754z926fzad5d682c3a40
On Subjectivity, Bias and Fairness in Language Model Learning
Gaci, Y. (2023) · theses.fr (ABES) · doi:10.70675/dca82074za0c4z46d1z8a6bz96ce30bea3b6
Transfer learning for abusive language detection
Bose, T. (2023) · theses.fr (ABES) · doi:10.70675/6b663c61zb592z4422zbc5fza68cbc285104
Advancing fairness in natural language processing : from traditional methods to explainability
Jourdan, F. (2024) · theses.fr (ABES) · doi:10.70675/b8535a05z82f1z46f7z9688z3cd35cea8381 · Cited by 3
TOXICHECK: A Unified Framework for Bias and Toxicity Evaluation in Large Language Models
Nandhakumar, C., & Vaishali, R. (2026) · International Conference on Artificial Intelligence and Machine Learning Applications Theme: Healthcare and Internet of Things (AIMLA) · doi:10.1109/aimla67915.2026.11522381
Counterfactual Data Augmentation using Locally Factored Dynamics
Pitis, S., Creager, E., & Garg, A. (2020) · arXiv · doi:10.48550/arxiv.2007.02863 · Cited by 26
“For example, [64] propose to reduce gender bias in natural language processing by generating counterfactual sentences with swapped gender pronouns.”
BackgroundVenkit, P. N., & Wilson, S. (2021) · arXiv · doi:10.48550/arxiv.2111.13259 · Cited by 14
“This is seen in the various works done for sociodemographic bias identification in textual analysis [26, 10, 25, 2, 5, 27].”
Background
Metadata
- Authors
- Park, J. H., Shin, J., & Fung, P.
- Affiliations
- Hong Kong University of Science and Technology (HK)
- Venue
- Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing
- Published
- 2018
- Pages
- 2799-2804
- OpenAlex
- W2888167352
- Cited by
- 323
- References
- 13
- Citations by year
- 2026: 1 · 2025: 23 · 2024: 26 · 2023: 56 · 2022: 53 · 2021: 75 · 2020: 53 · 2019: 34 · 2018: 2
- FWCI
- 16.75
- Type
- conference paper
- Language
- en
- Open access
- hybrid
- doi.org
- Licence
- cc-by
- Locations
- Conference on Empirical Methods in Natural Language Processing (EMNLP) (publishedVersion, cc-by)
- arXiv (Cornell University) (submittedVersion)
- Rare & Special e-Zone (The Hong Kong University of Science and Technology) (submittedVersion)
- arXiv (Cornell University)
- Funders
- Hong Kong University of Science and Technology
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Hate Speech and Cyberbullying Detection
- Physical Sciences › Computer Science › Artificial Intelligence › Ethics and Social Impacts of AI
- Physical Sciences › Computer Science › Artificial Intelligence › Sentiment Analysis and Opinion Mining
- Keywords
- offensive language detection, gender bias, model bias, bias mitigation, fine-tuning, imbalanced training data, word embeddings
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
