How Do Fairness Definitions Fare?: Examining Public Attitudes Towards Algorithmic Definitions of Fairness

By Nripsuta Ani Saxena, Karen Huang, Evan DeFilippis, Goran Radanovic, D. Parkes, Yang Liu. 2018

205 citations recorded by the source corpus.

What is the best way to define algorithmic fairness? While many definitions of fairness have been proposed in the computer science literature, there is no clear agreement over a particular definition. In this work, we investigate ordinary people's perceptions of three of these fairness definitions. Across two online experiments, we test which definitions people perceive to be the fairest in the context of loan decisions, and whether fairness perceptions change with the addition of sensitive information (i.e., race of the loan applicants). Overall, one definition (calibrated fairness) tends to be more pre- ferred than the others, and the results also provide support for the principle of affirmative action.

Subfields: Cognitive Neuroscience, Safety Research, Sociology and Political Science, AI Ethics, Fairness & Society

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Cognitive Neuroscience

In Safety Research

In Sociology and Political Science

In AI Ethics, Fairness & Society

Citations in the corpus

A Survey on Bias and Fairness in Machine Learning (2019, background): “ory of fairness definitions in the areas of education and machine-learning. In [122], authors listed and explained some of the definitions used for fairness in algorithmic classification problems. In [112], authors studied the general public’s perception of some of these fairness definitions from th”
Algorithmic bias: review, synthesis, and future research directions (2021, methodology): “In the context of loan decisions, Saxena et al. (2019) reported that people viewed ratio-based lending (i.e., splitting the money between the two candidates in proportion to their abilities to pay back their loans) as a fair method for giving loans to people.”
The ethics of algorithms: key problems and solutions (2020, unknown): “…the significant impact that algorithmic decisions have on people’s lives and the importance of context for choosing appropriate measures of fairness, it is surprising that there has been little effort to capture public views on algorithmic fairness (Lee et al. 2017; Saxena et al. 2019; Binns 2018).”
Machine Learning Testing: Survey, Landscapes and Horizons (2019, background): “[204] investigated people’s perceptions of three of the fairness definitions.”
Trustworthy Artificial Intelligence: A Review (2022, background): “• Fairness: Fairness of the system ensures that there is an absence of any discrimination or favoritism toward an individual or a group [136] based on any inherent or acquired characteristics that are irrelevant in the context of decision making [177].”