An official website of the United States government
The plethora of fairness metrics developed for ranking-based decision-making raises the question: which metrics align best with people’s perceptions of fairness, and why? Most prior studies examining people’s perceptions of fairness metrics tend to use ordinal rating scales (e.g., Likert scales). However, such scales can be ambiguous in their interpretation across participants, and can be influenced by interface features used to capture responses.We address this gap by exploring the use of two-alternative forced choice methodologies— used extensively outside the fairness community for comparing visual stimuli— to quantitatively compare participant perceptions across fairness metrics and ranking characteristics. We report a crowdsourced experiment with 224 participants across four conditions: two alternative rank fairness metrics, ARP and NDKL, and two ranking characteristics, lists of 20 and 100 candidates, resulting in over 170,000 individual judgments. Quantitative results show systematic differences in how people interpert these metrics, and surprising exceptions where fairness metrics disagree with people’s perceptions. Qualitative analyses of participant comments reveals an interplay between cognitive and visual strategies that affects people’s perceptions of fairness. From these results, we discuss future work in aligning fairness metrics with people’s perceptions, and highlight the need and benefits of expanding methodologies for fairness studies.
more »
« less
Balancing Act: Evaluating People’s Perceptions of Fair Ranking Metrics
Algorithmic decision-making using rankings— prevalent in areas from hiring and bail to university admissions— raises concerns of potential bias. In this paper, we explore the alignment between people’s perceptions of fairness and two popular fairness metrics designed for rankings. In a crowdsourced experiment with 480 participants, people rated the perceived fairness of a hypothetical scholarship distribution scenario. Results suggest a strong inclination towards relying on explicit score values. There is also evidence of people’s preference for one fairness metric, NDKL, over the other metric, ARP. Qualitative results paint a more complex picture: some participants endorse meritocratic award schemes and express concerns about fairness metrics being used to modify rankings; while other participants acknowledge socio-economic factors in score-based rankings as justification for adjusting rankings. In summary, we find that operationalizing algorithmic fairness in practice is a balancing act between mitigating harms towards marginalized groups and societal conventions of leveraging traditional performance scores such as grades in decision-making contexts.
more »
« less
- Award ID(s):
- 2007932
- PAR ID:
- 10530936
- Publisher / Repository:
- Proceedings of the 2024 ACM Conference on Fairness, Accountability, and Transparency
- Date Published:
- ISBN:
- 9798400704505
- Page Range / eLocation ID:
- 1940 to 1970
- Subject(s) / Keyword(s):
- Algorithmic Fairness Human Perception of Fairness
- Format(s):
- Medium: X
- Location:
- Rio de Janeiro, Brazil
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
With the increasing prevalence of automatic decision-making systems, concerns regarding the fairness of these systems also arise. Without a universally agreed-upon definition of fairness, given an automated decision-making scenario, researchers often adopt a crowdsourced approach to solicit people’s preferences across multiple fairness definitions. However, it is often found that crowdsourced fairness preferences are highly context-dependent, making it intriguing to explore the driving factors behind these preferences. One plausible hypothesis is that people’s fairness preferences reflect their perceived risk levels for different decision-making mistakes, such that the fairness definition that equalizes across groups the type of mistakes that are perceived as most serious will be preferred. To test this conjecture, we conduct a human-subject study (𝑁 =213) to study people’s fairness perceptions in three societal contexts. In particular, these three societal contexts differ on the expected level of risk associated with different types of decision mistakes, and we elicit both people’s fairness preferences and risk perceptions for each context. Our results show that people can often distinguish between different levels of decision risks across different societal contexts. However, we find that people’s fairness preferences do not vary significantly across the three selected societal contexts, except for within a certain subgroup of people (e.g., people with a certain racial background). As such, we observe minimal evidence suggesting that people’s risk perceptions of decision mistakes correlate with their fairness preference. These results highlight that fairness preferences are highly subjective and nuanced, and they might be primarily affected by factors other than the perceived risks of decision mistakes.more » « less
-
Abstract Decisions involving algorithmic rankings affect our lives in many ways, from product recommendations, receiving scholarships, to securing jobs. While tools have been developed for interactively constructing fair consensus rankings from a handful of rankings, addressing the more complex real‐world scenario— where diverse opinions are represented by a larger collection of rankings— remains a challenge. In this paper, we address these challenges by reformulating the exploration of rankings as a dimension reduction problem in a system called FairSpace. FairSpace provides new views, including Fair Divergence View and Cluster Views, by juxtaposing fairness metrics of different local and alternative global consensus rankings to aid ranking analysis tasks. We illustrate the effectiveness of FairSpace through a series of use cases, demonstrating via interactive workflows that users are empowered to create local consensuses by grouping rankings similar in their fairness or utility properties, followed by hierarchically aggregating local consensuses into a global consensus through direct manipulation. We discuss how FairSpace opens the possibility for advances in dimension reduction visualization to benefit the research area of supporting fair decision‐making in ranking based decision‐making contexts. Code, datasets and demo video available at:osf.io/d7cwkmore » « less
-
Algorithmic decisions often result in scoring and ranking individuals to determine credit worthiness, qualifications for college admissions and employment, and compatibility as dating partners. While automatic and seemingly objective, ranking algorithms can discriminate against individuals and protected groups, and exhibit low diversity. Furthermore, ranked results are often unstable -- small changes in the input data or in the ranking methodology may lead to drastic changes in the output, making the result uninformative and easy to manipulate. Similar concerns apply in cases where items other than individuals are ranked, including colleges, academic departments, or products. Despite the ubiquity of rankers, there is, to the best of our knowledge, no technical work that focuses on making rankers transparent. In this demonstration we present Ranking Facts, a Web-based application that generates a "nutritional label" for rankings. Ranking Facts is made up of a collection of visual widgets that implement our latest research results on fairness, stability, and transparency for rankings, and that communicate details of the ranking methodology, or of the output, to the end user. We will showcase Ranking Facts on real datasets from different domains, including college rankings, criminal risk assessment, and financial services.more » « less
-
As algorithmic decision making is increasingly deployed in every walk of life, many researchers have raised concerns about fairness-related bias from such algorithms. But there is little research on harnessing psychometric methods to uncover potential discriminatory bias inside decision-making algorithms. The main goal of this article is to propose a new framework for algorithmic fairness based on differential item functioning (DIF), which has been commonly used to measure item fairness in psychometrics. Our fairness notion, which we call differential algorithmic functioning (DAF), is defined based on three pieces of information: a decision variable, a “fair” variable, and a protected variable such as race or gender. Under the DAF framework, an algorithm can exhibit uniform DAF, nonuniform DAF, or neither (i.e., non-DAF). For detecting DAF, we provide modifications of well-established DIF methods: Mantel–Haenszel test, logistic regression, and residual-based DIF. We demonstrate our framework through a real dataset concerning decision-making algorithms for grade retention in K–12 education in the United States.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Conference Paper:
- https://doi.org/10.1145/3630106.3659018
