Takuya Yokota
ABSTRACT
Fairness-aware machine learning (ML) technology has been developed to remove discriminatory bias, e.g., bias on race and gender. However, there are trade-offs between the metrics of accuracy and fairness in ML models, and different stakeholders prioritize these metrics differently. Hence, to form an agreement on prioritization, workshop approaches encouraging dialogue among stakeholders have been explored. However, it is practically difficult for multiple stakeholders to have conversations at the same place and time. We examined a method of extracting the prioritization of several stakeholders regarding certain metrics using an online survey. We randomly divided 739 crowdsourced participants into 4 stakeholder groups and asked them to rank 5 randomly selected ML models in terms of their metric prioritization. Through this survey, we calculated the prioritization of metrics of each stakeholder group and whether the information on three other stakeholders affects another stakeholder’s prioritization of metrics. With our method, the prioritization of each stakeholder successfully met the requirements of their role. However, metric prioritization is not affected by information on the other stakeholders. Furthermore, demographics and attitudes towards decision making scenarios affect each stakeholder’s metric prioritization differently.
Supplemental Material
- Julia Angwin, Jeff Larson, Surya Mattu, and Lauren Kirchner. 2016. Machine Bias: There’s software used across the country to predict future criminals. And it’s biased against blacks.https://www.propublica.org/article/machine-bias-risk-assessments-in-criminal-sentencing Accessed: 2022-02-14.Google Scholar
- Solon Barocas, Moritz Hardt, and Arvind Narayanan. 2017. Fairness in machine learning. Nips tutorial 1(2017), 2.Google Scholar
- Reuben Binns. 2020. On the Apparent Conflict between Individual and Group Fairness. In Proceedings of the 2020 Conference on Fairness, Accountability, and Transparency (Barcelona, Spain) (FAT* ’20). Association for Computing Machinery, New York, NY, USA, 514–524. https://doi.org/10.1145/3351095.3372864Google ScholarDigital Library
- John M Carroll. 2000. Making Use: Scenario-Based Design of Human-Computer Interactions. MIT Press, London, England.Google ScholarDigital Library
- Pamela M. Casey, Jennifer K. Elek, Roger K. Warren, Fred Cheesman, Matt Kleiman, and Brian Ostrom. 2014. National Center for State Courts Offender Risk & Needs Assessment Instruments: A Primer for Courts. https://www.ncsc.org/__data/assets/pdf_file/0018/26226/bja-rna-final-report_combined-files-8-22-14.pdf. , Accessed: 2022-03-4.Google Scholar
- Alexandra Chouldechova. 2017. Fair prediction with disparate impact: A study of bias in recidivism prediction instruments. arxiv:1703.00056 [stat.AP]Google Scholar
- Andrew T. Collins and John M. Rose. 2005. Working paper: Estimation of stochastic scale with best-worst data. (2005). http://sydney.edu.au/business/itls/research/publications/working_papersGoogle Scholar
- Jonathan Dodge, Q. Vera Liao, Yunfeng Zhang, Rachel K. E. Bellamy, and Casey Dugan. 2019. Explaining Models: An Empirical Study of How Explanations Impact Fairness Judgment. In Proceedings of the 24th International Conference on Intelligent User Interfaces (Marina del Ray, California) (IUI ’19). Association for Computing Machinery, New York, NY, USA, 275–285. https://doi.org/10.1145/3301275.3302310Google ScholarDigital Library
- Ilana Golbin, Kyungha Kay Lim, and Divyanshi Galla. 2019. Curating Explanations of Machine Learning Models for Business Stakeholders. In 2019 Second International Conference on Artificial Intelligence for Industries (AI4I). 44–49. https://doi.org/10.1109/AI4I46381.2019.00019Google Scholar
- Galen Harrison, Julia Hanson, Christine Jacinto, Julio Ramirez, and Blase Ur. 2020. An Empirical Study on the Perceived Fairness of Realistic, Imperfect Machine Learning Models. In Proceedings of the 2020 Conference on Fairness, Accountability, and Transparency (Barcelona, Spain) (FAT* ’20). Association for Computing Machinery, New York, NY, USA, 392–402. https://doi.org/10.1145/3351095.3372831Google ScholarDigital Library
- Kenneth Holstein, Jennifer Wortman Vaughan, Hal Daumé, Miro Dudik, and Hanna Wallach. 2019. Improving Fairness in Machine Learning Systems: What Do Industry Practitioners Need?. In Proceedings of the 2019 CHI Conference on Human Factors in Computing Systems (Glasgow, Scotland Uk) (CHI ’19). Association for Computing Machinery, New York, NY, USA, 1–16. https://doi.org/10.1145/3290605.3300830Google ScholarDigital Library
- Patrick Janssen and Bert M. Sadowski. 2021. Bias in Algorithms: On the trade-off between accuracy and fairness(23rd Biennial Conference of the International Telecommunications Society (ITS): ”Digital societies and industrial transformations: Policies, markets, and technologies in a post-Covid world”, Online Conference / Gothenburg, Sweden, 21st-23rd June, 2021). International Telecommunications Society (ITS), Calgary. http://hdl.handle.net/10419/238032Google Scholar
- Maurice G Kendall. 1938. A new measure of rank correlation. Biometrika 30, 1/2 (1938), 81–93.Google ScholarCross Ref
- Min Kyung Lee, Daniel Kusbit, Anson Kahng, Ji Tae Kim, Xinran Yuan, Allissa Chan, Daniel See, Ritesh Noothigattu, Siheon Lee, Alexandros Psomas, and Ariel D. Procaccia. 2019. WeBuildAI: Participatory Framework for Algorithmic Governance. Proc. ACM Hum.-Comput. Interact. 3, CSCW, Article 181 (nov 2019), 35 pages. https://doi.org/10.1145/3359283Google ScholarDigital Library
- Keri Mallari, Kori Inkpen, Paul Johns, Sarah Tan, Divya Ramesh, and Ece Kamar. 2020. Do I Look Like a Criminal? Examining How Race Presentation Impacts Human Judgement of Recidivism. Association for Computing Machinery, New York, NY, USA, 1–13. https://doi.org/10.1145/3313831.3376257Google Scholar
- Ninareh Mehrabi, Fred Morstatter, Nripsuta Saxena, Kristina Lerman, and Aram Galstyan. 2021. A Survey on Bias and Fairness in Machine Learning. ACM Comput. Surv. 54, 6, Article 115 (jul 2021), 35 pages. https://doi.org/10.1145/3457607Google ScholarDigital Library
- 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 (Atlanta, GA, USA) (FAT* ’19). Association for Computing Machinery, New York, NY, USA, 220–229. https://doi.org/10.1145/3287560.3287596Google ScholarDigital Library
- Arvind Narayanan. 2018. Tutorial: 21 fairness definitions and their politics - YouTube. https://www.youtube.com/watch?v=jIXIuYdnyyk&list=WL&index=3&t=1633s. Accessed: 2021-12-02.Google Scholar
- Alun D. Preece, Dan Harborne, Dave Braines, Richard Tomsett, and Supriyo Chakraborty. 2018. Stakeholders in Explainable AI. CoRR abs/1810.00184(2018). arXiv:1810.00184http://arxiv.org/abs/1810.00184Google Scholar
- Gideon’s Promise, The National Legal Aid, Defenders Association, The National Association for Public Defense, and The National Association of Criminal Defense Lawyers. 2017. Joint statement in support of the use of pretrial risk assessment instruments. https://www.publicdefenders.us/files/Defenders%20Statement%20on%20Pretrial%20RAI%20May%202017.pdf. (Accessed on 04/25/2022).Google Scholar
- Debjani Saha, Candice Schumann, Duncan Mcelfresh, John Dickerson, Michelle Mazurek, and Michael Tschantz. 2020. Measuring Non-Expert Comprehension of Machine Learning Fairness Metrics. In Proceedings of the 37th International Conference on Machine Learning(Proceedings of Machine Learning Research, Vol. 119), Hal Daumé III and Aarti Singh (Eds.). PMLR, 8377–8387. https://proceedings.mlr.press/v119/saha20c.htmlGoogle ScholarDigital Library
- Hong Shen, Wesley H. Deng, Aditi Chattopadhyay, Zhiwei Steven Wu, Xu Wang, and Haiyi Zhu. 2021. Value Cards: An Educational Toolkit for Teaching Social Impacts of Machine Learning through Deliberation. In Proceedings of the 2021 ACM Conference on Fairness, Accountability, and Transparency (Virtual Event, Canada) (FAccT ’21). Association for Computing Machinery, New York, NY, USA, 850–861. https://doi.org/10.1145/3442188.3445971Google ScholarDigital Library
- Megha Srivastava, Hoda Heidari, and Andreas Krause. 2019. Mathematical Notions vs. Human Perception of Fairness: A Descriptive Approach to Fairness for Machine Learning. In Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining (Anchorage, AK, USA) (KDD ’19). Association for Computing Machinery, New York, NY, USA, 2459–2468. https://doi.org/10.1145/3292500.3330664Google ScholarDigital Library
- Niels van Berkel, Jorge Goncalves, Daniel Russo, Simo Hosio, and Mikael B. Skov. 2021. Effect of Information Presentation on Fairness Perceptions of Machine Learning Predictors. In Proceedings of the 2021 CHI Conference on Human Factors in Computing Systems (Yokohama, Japan) (CHI ’21). Association for Computing Machinery, New York, NY, USA, Article 245, 13 pages. https://doi.org/10.1145/3411764.3445365Google ScholarDigital Library
- Sebastiano Vigna. 2015. A Weighted Correlation Index for Rankings with Ties. In Proceedings of the 24th International Conference on World Wide Web (Florence, Italy) (WWW ’15). International World Wide Web Conferences Steering Committee, Republic and Canton of Geneva, CHE, 1166–1176. https://doi.org/10.1145/2736277.2741088Google Scholar
- Ruotong Wang, F. Maxwell Harper, and Haiyi Zhu. 2020. Factors Influencing Perceived Fairness in Algorithmic Decision-Making: Algorithm Outcomes, Development Procedures, and Individual Differences. In Proceedings of the 2020 CHI Conference on Human Factors in Computing Systems (Honolulu, HI, USA) (CHI ’20). Association for Computing Machinery, New York, NY, USA, 1–14. https://doi.org/10.1145/3313831.3376813Google ScholarDigital Library
- Xinru Wang and Ming Yin. 2021. Are Explanations Helpful? A Comparative Study of the Effects of Explanations in AI-Assisted Decision-Making. Association for Computing Machinery, New York, NY, USA, 318–328. https://doi.org/10.1145/3397481.3450650Google ScholarDigital Library
- Yongnian Zheng and Juan Ruiz Toribio. 2021. The role of transparency in multi-stakeholder educational recommendations. User Model. User Adapt. Interact. 31 (2021), 513–540.Google ScholarDigital Library
Recommendations
A Survey on Machine Learning Based Requirement Prioritization Techniques
CIIS '18: Proceedings of the 2018 International Conference on Computational Intelligence and Intelligent SystemsSoftware is becoming a need of today's business and everyday tasks. However, building software that fulfils its user's need is not an easy task. It is deemed important to properly elicit and prioritise the requirements of users and these prioritized ...
Clustering stakeholders for requirements decision making
REFSQ'11: Proceedings of the 17th international working conference on Requirements engineering: foundation for software quality[Context and motivation] Novel web-based requirements elicitation tools offer the possibility to collect requirements preferences from large number of stakeholders. Such tools have the potential to provide useful data for requirements prioritization and ...
Network structure and requirements crowdsourcing for OSS projects
AbstractCrowdsourcing system requirements enables project managers to elicit feedback from a broader range of stakeholders. The advantages of crowdsourcing include a higher volume of requirements reflecting a more comprehensive array of use cases and a ...
Comments