[go: up one dir, main page]
More Web Proxy on the site http://driver.im/ skip to main content
10.1145/3308560.3317593acmotherconferencesArticle/Chapter ViewAbstractPublication PagesthewebconfConference Proceedingsconference-collections
research-article

Nuanced Metrics for Measuring Unintended Bias with Real Data for Text Classification

Published: 13 May 2019 Publication History

Abstract

Unintended bias in Machine Learning can manifest as systemic differences in performance for different demographic groups, potentially compounding existing challenges to fairness in society at large. In this paper, we introduce a suite of threshold-agnostic metrics that provide a nuanced view of this unintended bias, by considering the various ways that a classifier’s score distribution can vary across designated groups. We also introduce a large new test set of online comments with crowd-sourced annotations for identity references. We use this to show how our metrics can be used to find new and potentially subtle unintended bias in existing public models.

References

[1]
Alex Beutel, Jilin Chen, Zhe Zhao, and Ed H. Chi. 2017. Data Decisions and Theoretical Implications when Adversarially Learning Fair Representations. CoRR abs/1707.00075(2017). http://arxiv.org/abs/1707.00075
[2]
Daniel Borkan, Lucas Dixon, John Li, Jeffrey Sorensen, Nithum Thain, and Lucy Vasserman. 2019. Limitations of Pinned AUC for Measuring Unintended Bias. CoRR (2019).
[3]
Tim Brennan, William Dieterich, and Beate Ehret. 2009. Evaluating the Predictive Validity of the Compas Risk and Needs Assessment System. Criminal Justice and Behavior 36, 1 (2009), 21–40. arXiv:https://doi.org/10.1177/0093854808326545
[4]
Joy Buolamwini and Timnit Gebru. 2018. Gender Shades: Intersectional Accuracy Disparities in Commercial Gender Classification. In Proceedings of the 1st Conference on Fairness, Accountability and Transparency(Proceedings of Machine Learning Research), Sorelle A. Friedler and Christo Wilson (Eds.), Vol. 81. PMLR, New York, NY, USA, 77–91. http://proceedings.mlr.press/v81/buolamwini18a.html
[5]
Lucas Dixon, John Li, Jeffrey Sorensen, Nithum Thain, and Lucy Vasserman. 2018. Measuring and Mitigating Unintended Bias in Text Classification. In Proceedings of AAAI/ACM Conference on Artificial Intelligence, Ethics, and Society.
[6]
Yanai Elazar and Yoav Goldberg. 2018. Adversarial Removal of Demographic Attributes from Text Data. In Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing. Association for Computational Linguistics, 11–21. http://aclweb.org/anthology/D18-1002
[7]
Michael Feldman, Sorelle A. Friedler, John Moeller, Carlos Scheidegger, and Suresh Venkatasubramanian. 2015. Certifying and Removing Disparate Impact. In Proceedings of the 21th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining(KDD ’15). ACM, New York, NY, USA, 259–268.
[8]
Sorelle A. Friedler, Carlos Scheidegger, and Suresh Venkatasubramanian. 2016. On the (im)possibility of fairness. CoRR abs/1609.07236(2016). http://arxiv.org/abs/1609.07236
[9]
Sahaj Garg, Vincent Perot, Nicole Limtiaco, Ankur Taly, Ed H. Chi, and Alex Beutel. 2018. Counterfactual Fairness in Text Classification through Robustness. CoRR abs/1809.10610(2018). arxiv:1809.10610http://arxiv.org/abs/1809.10610
[10]
Moritz Hardt, Eric Price, and Nathan Srebro. 2016. Equality of Opportunity in Supervised Learning. CoRR abs/1610.02413(2016). http://arxiv.org/abs/1610.02413
[11]
Jigsaw. 2017. Perspective API. https://www.perspectiveapi.com/
[12]
Jon M. Kleinberg, Sendhil Mullainathan, and Manish Raghavan. 2016. Inherent Trade-Offs in the Fair Determination of Risk Scores. CoRR abs/1609.05807(2016). http://arxiv.org/abs/1609.05807
[13]
Lucy Vasserman, John Li, CJ Adams, Lucas Dixon. 2018. Unintended bias and names of frequently targeted groups. https://medium.com/the-false-positive/unintended-bias-and-names-of-frequently-targeted-groups-8e0b81f80a23
[14]
S. J. Mason and N. E. Graham. {n. d.}. Areas beneath the relative operating characteristics (ROC) and relative operating levels (ROL) curves: Statistical significance and interpretation. Quarterly Journal of the Royal Meteorological Society 128, 584 ({n. d.}), 2145–2166. arXiv:https://rmets.onlinelibrary.wiley.com/doi/pdf/10.1256/003590002320603584
[15]
Aditya Krishna Menon and Robert C Williamson. 2018. The cost of fairness in binary classification. In Proceedings of the 1st Conference on Fairness, Accountability and Transparency(Proceedings of Machine Learning Research), Sorelle A. Friedler and Christo Wilson (Eds.), Vol. 81. PMLR, New York, NY, USA, 107–118. http://proceedings.mlr.press/v81/menon18a.html
[16]
Margaret Mitchell, Simone Wu, Andrew Zaldivar, Parker Barnes, Lucy Vasserman, Ben Hutchinson, Elena Spitzer, Inioluwa Deborah Raji, and Timnit Gebru. 2019. Model Cards for Model Reporting. In Proceedings of the Conference on Fairness, Accountability, and Transparency(FAT* ’19). ACM, New York, NY, USA, 220–229.
[17]
Ji Ho Park, Jamin Shin, and Pascale Fung. 2018. Reducing Gender Bias in Abusive Language Detection. In Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing. Association for Computational Linguistics, 2799–2804. http://aclweb.org/anthology/D18-1302
[18]
Nithum Thain, Lucas Dixon, and Ellery Wulczyn. 2017. Wikipedia Talk Labels: Toxicity. (2 2017).
[19]
Ellery Wulczyn, Nithum Thain, and Lucas Dixon. 2017. Ex machina: Personal attacks seen at scale. In Proceedings of the 26th International Conference on World Wide Web. International World Wide Web Conferences Steering Committee, 1391–1399.

Cited By

View all
  • (2024)What Is Wrong with My Model? Identifying Systematic Problems with Semantic Data SlicingProceedings of the 39th IEEE/ACM International Conference on Automated Software Engineering10.1145/3691620.3695033(306-318)Online publication date: 27-Oct-2024
  • (2024)Harnessing the Power of LLMs in Practice: A Survey on ChatGPT and BeyondACM Transactions on Knowledge Discovery from Data10.1145/364950618:6(1-32)Online publication date: 26-Apr-2024
  • (2024)Model-Agnostic Random Weighting for Out-of-Distribution GeneralizationProceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining10.1145/3637528.3671762(1050-1061)Online publication date: 25-Aug-2024
  • Show More Cited By

Index Terms

  1. Nuanced Metrics for Measuring Unintended Bias with Real Data for Text Classification
          Index terms have been assigned to the content through auto-classification.

          Recommendations

          Comments

          Please enable JavaScript to view thecomments powered by Disqus.

          Information & Contributors

          Information

          Published In

          cover image ACM Other conferences
          WWW '19: Companion Proceedings of The 2019 World Wide Web Conference
          May 2019
          1331 pages
          ISBN:9781450366755
          DOI:10.1145/3308560
          Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than ACM must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected]

          In-Cooperation

          • IW3C2: International World Wide Web Conference Committee

          Publisher

          Association for Computing Machinery

          New York, NY, United States

          Publication History

          Published: 13 May 2019

          Permissions

          Request permissions for this article.

          Check for updates

          Qualifiers

          • Research-article
          • Research
          • Refereed limited

          Conference

          WWW '19
          WWW '19: The Web Conference
          May 13 - 17, 2019
          San Francisco, USA

          Acceptance Rates

          Overall Acceptance Rate 1,899 of 8,196 submissions, 23%

          Contributors

          Other Metrics

          Bibliometrics & Citations

          Bibliometrics

          Article Metrics

          • Downloads (Last 12 months)224
          • Downloads (Last 6 weeks)33
          Reflects downloads up to 11 Dec 2024

          Other Metrics

          Citations

          Cited By

          View all
          • (2024)What Is Wrong with My Model? Identifying Systematic Problems with Semantic Data SlicingProceedings of the 39th IEEE/ACM International Conference on Automated Software Engineering10.1145/3691620.3695033(306-318)Online publication date: 27-Oct-2024
          • (2024)Harnessing the Power of LLMs in Practice: A Survey on ChatGPT and BeyondACM Transactions on Knowledge Discovery from Data10.1145/364950618:6(1-32)Online publication date: 26-Apr-2024
          • (2024)Model-Agnostic Random Weighting for Out-of-Distribution GeneralizationProceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining10.1145/3637528.3671762(1050-1061)Online publication date: 25-Aug-2024
          • (2024)Auditing GPT's Content Moderation Guardrails: Can ChatGPT Write Your Favorite TV Show?Proceedings of the 2024 ACM Conference on Fairness, Accountability, and Transparency10.1145/3630106.3658932(660-686)Online publication date: 3-Jun-2024
          • (2024)Accuracy and Fairness for Web-Based Content Analysis under Temporal Shifts and Delayed LabelingProceedings of the 16th ACM Web Science Conference10.1145/3614419.3644028(268-278)Online publication date: 21-May-2024
          • (2024)Wikibench: Community-Driven Data Curation for AI Evaluation on WikipediaProceedings of the 2024 CHI Conference on Human Factors in Computing Systems10.1145/3613904.3642278(1-24)Online publication date: 11-May-2024
          • (2024)OODREB: Benchmarking State-of-the-Art Methods for Out-Of-Distribution Generalization on Relation ExtractionProceedings of the ACM Web Conference 202410.1145/3589334.3645695(2294-2303)Online publication date: 13-May-2024
          • (2024)Using Early Readouts to Mediate Featural Bias in Distillation2024 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)10.1109/WACV57701.2024.00262(2626-2635)Online publication date: 3-Jan-2024
          • (2024)You Only Prompt Once: On the Capabilities of Prompt Learning on Large Language Models to Tackle Toxic Content2024 IEEE Symposium on Security and Privacy (SP)10.1109/SP54263.2024.00061(770-787)Online publication date: 19-May-2024
          • (2024)LLM Diagnostic Toolkit: Evaluating LLMs for Ethical Issues2024 International Joint Conference on Neural Networks (IJCNN)10.1109/IJCNN60899.2024.10650995(1-8)Online publication date: 30-Jun-2024
          • Show More Cited By

          View Options

          Login options

          View options

          PDF

          View or Download as a PDF file.

          PDF

          eReader

          View online with eReader.

          eReader

          HTML Format

          View this article in HTML Format.

          HTML Format

          Media

          Figures

          Other

          Tables

          Share

          Share

          Share this Publication link

          Share on social media