mlsanityData to 7 Oct 2026

Examining Gender and Race Bias in Two Hundred Sentiment Analysis Systems

arXiv 1805.04508 ↗First posted 11 May 2018cs.CLcited by 234

Not on the map. Why?

Abstract (arXiv)

Automatic machine learning systems can inadvertently accentuate and perpetuate inappropriate human biases. Past work on examining inappropriate biases has largely focused on just individual systems. Further, there is no benchmark dataset for examining inappropriate biases in systems. Here for the first time, we present the Equity Evaluation Corpus (EEC), which consists of 8,640 English sentences carefully chosen to tease out biases towards certain races and genders. We use the dataset to examine 219 automatic sentiment analysis systems that took part in a recent shared task, SemEval-2018 Task 1 'Affect in Tweets'. We find that several of the systems show statistically significant bias; that is, they consistently provide slightly higher sentiment intensity predictions for one race or one gender. We make the EEC freely available.

Key facts. Cited by 234 papers in the map (data through 7 Oct 2026). First posted on arXiv 11 May 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 41; 2022: 44; 2023: 65; 2024: 41; 2025: 30; 2026: 13.

234 papers.

Sort:

By area:

  1. 2021Scaling Language Models: Methods, Analysis & Insights from Training Gophercited by 1,199
  2. 2023Bias and Fairness in Large Language Models: A Surveycited by 626
  3. 2021BOLD: Dataset and Metrics for Measuring Biases in Open-Ended Language Generationcited by 410
  4. 2023Evaluating Verifiability in Generative Search Enginescited by 297
  5. 2023Large Language Model Alignment: A Surveycited by 241
  6. 2021Societal Biases in Language Generation: Progress and Challengescited by 201
  7. 2021What Will it Take to Fix Benchmarking in Natural Language Understanding?cited by 200
  8. 2023Gender bias and stereotypes in Large Language Modelscited by 185
  9. 2021Bias Out-of-the-Box: An Empirical Analysis of Intersectional Occupational Biases in Popular Generative Language Modelscited by 141
  10. 2021Understanding and Evaluating Racial Biases in Image Captioningcited by 108
  11. 2021Detoxifying Language Models Risks Marginalizing Minority Voicescited by 106
  12. 2022XAI for Transformers: Better Explanations through Conservative Propagationcited by 100
38 more
  1. 2021Trustworthy AI: A Computational Perspectivecited by 93
  2. 2023A Survey on Fairness in Large Language Modelscited by 91
  3. 2021A Survey on Gender Bias in Natural Language Processingcited by 89
  4. 2021Quantifying Social Biases in NLP: A Generalization and Empirical Comparison of Extrinsic Fairness Metricscited by 83
  5. 2024A Survey on Multilingual Large Language Models: Corpora, Alignment, and Biascited by 82
  6. 2021On Measures of Biases and Harms in NLPcited by 81
  7. 2021What's in the Box? A Preliminary Analysis of Undesirable Content in the Common Crawl Corpuscited by 79
  8. 2024Bias in Large Language Models: Origin, Evaluation, and Mitigationcited by 77
  9. 2021FairFil: Contrastive Neural Debiasing Method for Pretrained Text Encoderscited by 75
  10. 2021A Survey of Race, Racism, and Anti-Racism in NLPcited by 74
  11. 2021Towards generalisable hate speech detection: a review on obstacles and solutionscited by 66
  12. 2021Collecting a Large-Scale Gender Bias Dataset for Coreference Resolution and Machine Translationcited by 62
  13. 2022Theories of "Gender" in NLP Bias Researchcited by 62
  14. 2021Stereotype and Skew: Quantifying Gender Bias in Pre-trained and Fine-tuned Language Modelscited by 57
  15. 2024Fairness in Large Language Models: A Taxonomic Surveycited by 57
  16. 2022Re-contextualizing Fairness in NLP: The Case of Indiacited by 55
  17. 2023Bias Against 93 Stigmatized Groups in Masked Language Models and Downstream Sentiment Classification Taskscited by 51
  18. 2021Diverse Adversaries for Mitigating Bias in Trainingcited by 48
  19. 2022Debiasing isn't enough! -- On the Effectiveness of Debiasing MLMs and their Social Biases in Downstream Taskscited by 48
  20. 2022VALUE: Understanding Dialect Disparity in NLUcited by 45
  21. 2021Robust Contrastive Learning Using Negative Samples with Diminished Semanticscited by 43
  22. 2023A Survey on Intersectional Fairness in Machine Learning: Notions, Mitigation, and Challengescited by 41
  23. 2023Benefits and Harms of Large Language Models in Digital Mental Healthcited by 39
  24. 2022Quantifying Social Biases Using Templates is Unreliablecited by 38
  25. 2023Evaluation of African American Language Bias in Natural Language Generationcited by 36
  26. 2022Fewer Errors, but More Stereotypes? The Effect of Model Size on Gender Biascited by 33
  27. 2022Does Moral Code Have a Moral Code? Probing Delphi's Moral Philosophycited by 31
  28. 2021Unpacking the Interdependent Systems of Discrimination: Ableist Bias in NLP Systems through an Intersectional Lenscited by 30
  29. 2022Choose Your Lenses: Flaws in Gender Bias Evaluationcited by 29
  30. 2023Social Bias Probing: Fairness Benchmarking for Language Modelscited by 29
  31. 2021Influence Tuning: Demoting Spurious Correlations via Instance Attribution and Instance-Driven Updatescited by 27
  32. 2023Sociodemographic Bias in Language Models: A Survey and Forward Pathcited by 27
  33. 2023Survey of Social Bias in Vision-Language Modelscited by 26
  34. 2023Building Socio-culturally Inclusive Stereotype Resources with Community Engagementcited by 25
  35. 2021Assessing Fairness in the Presence of Missing Datacited by 24
  36. 2022Xplique: A Deep Learning Explainability Toolboxcited by 24
  37. 2023An Empirical Study of Metrics to Measure Representational Harms in Pre-Trained Language Modelscited by 24
  38. 2023Explanation-based Finetuning Makes Models More Robust to Spurious Cuescited by 24

50 most cited of 234 All 234 (JSON)