Effect of Information Presentation on Fairness Perceptions of Machine Learning Predictors

The uptake of artificial intelligence-based applications raises concerns about the fairness and transparency of AI behaviour. Consequently, the Computer Science community calls for the involvement of the general public in the design and evaluation of AI systems. Assessing the fairness of individual predictors is an essential step in the development of equitable algorithms. In this study, we evaluate the effect of two common visualisation techniques (text-based and scatterplot) and the display of the outcome information (i.e., ground-truth) on the perceived fairness of predictors. Our results from an online crowdsourcing study (N = 80) show that the chosen visualisation technique significantly alters people’s fairness perception and that the presented scenario, as well as the participant’s gender and past education, influence perceived fairness. Based on these results we draw recommendations for future work that seeks to involve non-experts in AI fairness evaluations.

• Publication year

  2021

• Venue

  International Conference on Human Factors in Computing Systems

• Publication date

  2021-05-06

• Fields of study

  Computer Science

• Identifiers
  DOI 10.1145/3411764.3445365
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• Questioning the AI: Informing Design Practices for Explainable AI User Experiences

  2020cited by this paper
• Designing Alternative Representations of Confusion Matrices to Support Non-Expert Public Understanding of Algorithm Performance

  2020cited by this paper
• A Systematic Assessment of National Artificial Intelligence Policies: Perspectives from the Nordics and Beyond

  2020cited by this paper
• Will the Crowd Game the Algorithm?: Using Layperson Judgments to Combat Misinformation on Social Media by Downranking Distrusted Sources

  2020cited by this paper
• Human-centred artificial intelligence: a contextual morality perspective

  2020cited by this paper
• Factors Influencing Perceived Fairness in Algorithmic Decision-Making: Algorithm Outcomes, Development Procedures, and Individual Differences

  2020influential reference
• Interpreting Interpretability: Understanding Data Scientists' Use of Interpretability Tools for Machine Learning

  2020influential reference
• Human Decision Making with Machine Assistance

  2019cited by this paper
• Definitions, methods, and applications in interpretable machine learning

  2019cited by this paper
• Crowdsourcing Perceptions of Fair Predictors for Machine Learning

  2019influential reference
• Trends and Applications of Machine Learning in Quantitative Finance

  2019cited by this paper
• The What-If Tool: Interactive Probing of Machine Learning Models

  2019influential reference
• Gender trends in computer science authorship

  2019cited by this paper
• Explaining Decision-Making Algorithms through UI: Strategies to Help Non-Expert Stakeholders

  2019influential reference
• Fueling AI with public displays?: a feasibility study of collecting biometrically tagged consensual data on a university campus

  2019cited by this paper
• Gamut: A Design Probe to Understand How Data Scientists Understand Machine Learning Models

  2019influential reference
• Comparing Effectiveness and Engagement of Data Comics and Infographics

  2019cited by this paper
• Using the Short Graph Literacy Scale to Predict Precursors of Health Behavior Change

  2019influential reference
• Mathematical Notions vs. Human Perception of Fairness: A Descriptive Approach to Fairness for Machine Learning

  2019influential reference
• The roles of alternative data and machine learning in fintech lending: Evidence from the LendingClub consumer platform

  2019cited by this paper
• Keeping Designers in the Loop: Communicating Inherent Algorithmic Trade-offs Across Multiple Objectives

  2019influential reference
• Artificial Intelligence and Policing: First Questions

  2018cited by this paper
• Human Perceptions of Fairness in Algorithmic Decision Making: A Case Study of Criminal Risk Prediction

  2018influential reference
• 'It's Reducing a Human Being to a Percentage': Perceptions of Justice in Algorithmic Decisions

  2018cited by this paper
• Using Animation to Alleviate Overdraw in Multiclass Scatterplot Matrices

  2018cited by this paper
• A Qualitative Exploration of Perceptions of Algorithmic Fairness

  2018cited by this paper
• More Text Please! Understanding and Supporting the Use of Visualization for Clinical Text Overview

  2018cited by this paper
• The Moral Machine experiment

  2018cited by this paper
• ggeffects: Tidy Data Frames of Marginal Effects from Regression Models

  2018cited by this paper
• How Do Fairness Definitions Fare?: Examining Public Attitudes Towards Algorithmic Definitions of Fairness

  2018cited by this paper
• Ethical Dimensions of Visualization Research

  2018cited by this paper
• Bots, Bias and Big Data: Artificial Intelligence, Algorithmic Bias and Disparate Impact Liability in Hiring Practices

  2018cited by this paper
• Fairness in Criminal Justice Risk Assessments: The State of the Art

  2017cited by this paper
• Calibrated Fairness in Bandits

  2017cited by this paper
• Demographics and discussion influence views on algorithmic fairness

  2017cited by this paper
• An Empirical Study on the Reliability of Perceiving Correlation Indices using Scatterplots

  2017cited by this paper
• Fairness in Learning: Classic and Contextual Bandits

  2016cited by this paper
• False Positives, False Negatives, and False Analyses: A Rejoinder to "Machine Bias: There's Software Used across the Country to Predict Future Criminals. and It's Biased against Blacks"

  2016cited by this paper
• “Why Should I Trust You?”: Explaining the Predictions of Any Classifier

  2016cited by this paper
• Equality of Opportunity in Supervised Learning

  2016cited by this paper
• Risk assessment in social lending via random forests

  2015cited by this paper
• Fitting Linear Mixed-Effects Models Using lme4

  2014cited by this paper
• Are you sure your software is gender-neutral?

  2014cited by this paper
• Crowdsourcing on the spot: altruistic use of public displays, feasibility, performance, and behaviours

  2013cited by this paper
• Communicating quantitative information about unexploded ordnance risks to the public.

  2013cited by this paper
• Parental Religiosity and Children's Educational Attainment in the United States

  2012cited by this paper
• Evaluating Online Labor Markets for Experimental Research: Amazon.com's Mechanical Turk

  2012cited by this paper
• The impact of social information on visual judgments

  2011cited by this paper
• Fairness through awareness

  2011cited by this paper
• Three naive Bayes approaches for discrimination-free classification

  2010cited by this paper
• The Effect of Format on Parents' Understanding of the Risks and Benefits of Clinical Research: A Comparison Between Text, Tables, and Graphics

  2010influential reference
• Why and why not explanations improve the intelligibility of context-aware intelligent systems

  2009cited by this paper
• Generalized linear mixed models: a practical guide for ecology and evolution.

  2009influential reference
• Statistical power analyses using G*Power 3.1: Tests for correlation and regression analyses

  2009cited by this paper
• Crowdsourcing user studies with Mechanical Turk

  2008cited by this paper
• Multivariate Data Analysis

  2007cited by this paper
• Automated Decision Making Comes of Age

  2005cited by this paper
• Which is the Fair Sex? Gender Differences in Altruism

  2001cited by this paper
• Unskilled and unaware of it: how difficulties in recognizing one's own incompetence lead to inflated self-assessments.

  1999cited by this paper
• Variables on Scatterplots Look More Highly Correlated When the Scales Are Increased

  1982cited by this paper
• Unskilled and Unaware of It : How Difficulties in Recognizing One ’ s Own Incompetence Lead to Inflated Self-Assessments

  year unknowncited by this paper

• When Life Gives You AI, Will You Turn It Into A Market for Lemons? Understanding How Information Asymmetries About AI System Capabilities Affect Market Outcomes and Adoption

  2026cites this paper
• Exploring AI competency in Chinese undergraduates through the UNESCO framework.

  2026cites this paper
• User Reliance on AI Support for Collaborative Partner Selection

  2026cites this paper
• Designing Effective Training Dataset Explanations: The Impact of Information Depth and Progressive Disclosure

  2026cites this paper
• Algorithm appreciation or aversion: the effects of accuracy disclosure on users' reliance on algorithmic suggestions

  2025cites this paper
• Your Model Is Unfair, Are You Even Aware? Inverse Relationship Between Comprehension and Trust in Explainability Visualizations of Biased ML Models

  2025cites this paper
• Why Users Reject AI Counselors? The Mediating Role of Trust and Perceived Self-Correction Ability in Imperfect Experiences

  2025cites this paper
• AI Ethics and Fairness in Machine Learning: Promoting Fairness in Critical Engineering Systems

  2025cites this paper
• AI Ethics in Engineering: Enhancing Fairness in Machine Learning Models for Critical Systems

  2025cites this paper
• Effort-aware Fairness: Incorporating a Philosophy-informed, Human-centered Notion of Effort into Algorithmic Fairness Metrics

  2025cites this paper
• Exploring the impact of explainable AI and cognitive capabilities on users’ decisions

  2025cites this paper
• Towards Effective Human Intervention in Algorithmic Decision-Making: Understanding the Effect of Decision-Makers' Configuration on Decision-Subjects' Fairness Perceptions

  2025cites this paper
• "Good" XAI Design: For What? In Which Ways?

  2025cites this paper
• Counselor type (Human/AI) and consultation intention: a moderated mediation model of trust and psychological counseling scenarios

  2025cites this paper
• Guidelines for designing visualization tools for group fairness analysis in binary classification

  2025cites this paper
• Towards Multi-stakeholder Evaluation of ML Models: A Crowdsourcing Study on Metric Preferences in Job-Matching System

  2025cites this paper
• Leveraging Complementary AI Explanations to Mitigate Misunderstanding in XAI

  2025cites this paper
• From Text to Trust: Empowering AI-assisted Decision Making with Adaptive LLM-powered Analysis

  2025cites this paper
• Impact of Explanation Techniques and Representations on Users' Comprehension and Confidence in Explainable AI

  2025cites this paper
• AI: Friend or foe of fairness perceptions of the tax administration? A survey experiment on citizens' procedural fairness perceptions

  2025cites this paper
• Biased Minds Meet Biased AI: How Class Imbalance Shapes Appropriate Reliance and Interacts with Human Base Rate Neglect

  2025cites this paper
• "Over-the-Hood" AI Inclusivity Bugs and How 3 AI Product Teams Found and Fixed Them

  2025cites this paper
• Identifying Algorithmic Decision Subjects' Needs for Meaningful Contestability

  2025cites this paper
• Actionable Recourse for Automated Decisions: Examining the Effects of Counterfactual Explanation Type and Presentation on Lay User Understanding

  2024cites this paper
• Decoding AI's Nudge: A Unified Framework to Predict Human Behavior in AI-assisted Decision Making

  2024cites this paper
• Grading by AI makes me feel fairer? How different evaluators affect college students’ perception of fairness

  2024cites this paper
• Are We Asking the Right Questions?: Designing for Community Stakeholders’ Interactions with AI in Policing

  2024cites this paper
• OpenHEXAI: An Open-Source Framework for Human-Centered Evaluation of Explainable Machine Learning

  2024cites this paper
• A Canary in the AI Coal Mine: American Jews May Be Disproportionately Harmed by Intellectual Property Dispossession in Large Language Model Training

  2024cites this paper
• Public Perceptions of Fairness Metrics Across Borders

  2024cites this paper
• Do Crowdsourced Fairness Preferences Correlate with Risk Perceptions?

  2024cites this paper
• Blind Spots and Biases: Exploring the Role of Annotator Cognitive Biases in NLP

  2024cites this paper
• Why the Fine, AI? The Effect of Explanation Level on Citizens' Fairness Perception of AI-based Discretion in Public Administrations

  2024cites this paper
• Dealing with Uncertainty: Understanding the Impact of Prognostic Versus Diagnostic Tasks on Trust and Reliance in Human-AI Decision Making

  2024cites this paper
• Computational Notebook as a Tool for Supporting Black Engineers Non-Profit Organizations in the Context of Workforce Participation

  2024cites this paper
• I lose vs. I earn: Consumer perceived price fairness toward algorithmic (vs. human) price discrimination

  2024cites this paper
• Who Made That Decision and Why? Users’ Perceptions of Human Versus AI Decision-Making and the Power of Explainable-AI

  2024cites this paper
• Students’ perspectives on using digital tools in programming courses

  2024cites this paper
• Algorithm Bias and Perceived Fairness: A Comprehensive Scoping Review

  2024cites this paper
• Impact of interaction technique in interactive data visualisations: A study on lookup, comparison, and relation-seeking tasks

  2024cites this paper
• Reducing the incidence of biased algorithmic decisions through feature importance transparency: an empirical study

  2024cites this paper
• Trust in Artificial Intelligence: Beyond Interpretability

  2024cites this paper
• Supporting User Critiques of AI Systems via Training Dataset Explanations: Investigating Critique Properties and the Impact of Presentation Style

  2024cites this paper
• Towards Human-centered Design of Explainable Artificial Intelligence (XAI): A Survey of Empirical Studies

  2024cites this paper
• The Explanation That Hits Home: The Characteristics of Verbal Explanations That Affect Human Perception in Subjective Decision-Making

  2024cites this paper
• Ethics in the Age of Algorithms: Unravelling the Impact of Algorithmic Unfairness on Data Analytics Recommendation Acceptance

  2024cites this paper
• Judging in the Dark: How Delivery Riders Form Fairness Perceptions Under Algorithmic Management

  2024cites this paper
• Humans or Machines for Teaching: Trust and Preferences among University Students

  2024cites this paper
• Position: Towards Bidirectional Human-AI Alignment

  2024cites this paper
• Who should be first? How and when AI-human order influences procedural justice in a multistage decision-making process

  2023cites this paper
• A Critical Survey on Fairness Benefits of Explainable AI

  2023cites this paper
• Helpful, Misleading or Confusing: How Humans Perceive Fundamental Building Blocks of Artificial Intelligence Explanations

  2023cites this paper
• Assessing Perceived Fairness from Machine Learning Developer's Perspective

  2023cites this paper
• Differential Fairness: An Intersectional Framework for Fair AI

  2023cites this paper
• Making Smart Cities Explainable: What XAI Can Learn from the “Ghost Map”

  2023cites this paper
• Who Do We Mean When We Talk About Visualization Novices?

  2023cites this paper
• Disentangling Fairness Perceptions in Algorithmic Decision-Making: the Effects of Explanations, Human Oversight, and Contestability

  2023cites this paper
• Fairness Perceptions of Artificial Intelligence: A Review and Path Forward

  2023cites this paper
• Towards a Science of Human-AI Decision Making: An Overview of Design Space in Empirical Human-Subject Studies

  2023cites this paper
• Help or Hinder? Evaluating the Impact of Fairness Metrics and Algorithms in Visualizations for Consensus Ranking

  2023cites this paper
• Welfarist Moral Grounding for Transparent AI

  2023cites this paper
• A Missing Piece in the Puzzle: Considering the Role of Task Complexity in Human-AI Decision Making

  2023influential citation
• Adaptation of AI Explanations to Users’ Roles

  2023cites this paper
• My Model is Unfair, Do People Even Care? Visual Design Affects Trust and Perceived Bias in Machine Learning

  2023influential citation
• Perceived Algorithmic Fairness using Organizational Justice Theory: An Empirical Case Study on Algorithmic Hiring

  2023cites this paper
• Comprehension is a double-edged sword: Over-interpreting unspecified information in intelligible machine learning explanations

  2023cites this paper
• How Stated Accuracy of an AI System and Analogies to Explain Accuracy Affect Human Reliance on the System

  2023cites this paper
• A Critical Survey on Fairness Benefits of XAI

  2023cites this paper
• Information provision measures for voice agent product recommendations— The effect of process explanations and process visualizations on fairness perceptions

  2023cites this paper
• Auditing Machine Behaviors: Does a diverse crowd result in different social norms?

  2023cites this paper
• The Influence of Content Presentation on Users’ Intention to Adopt mHealth Applications: Based on the S-O-R Theoretical Model

  2022cites this paper
• 2022

  2022cites this paper
• Explaining automated decision-making: a multinational study of the GDPR right to meaningful information

  2022cites this paper
• Recruiting Software Engineers on Prolific

  2022cites this paper
• Measurements, Algorithms, and Presentations of Reality: Framing Interactions with AI-Enabled Decision Support

  2022cites this paper
• Do Humans Prefer Debiased AI Algorithms? A Case Study in Career Recommendation

  2022cites this paper
• The methodology of studying fairness perceptions in Artificial Intelligence: Contrasting CHI and FACCT

  2022cites this paper
• "I'm not sure what difference is between their content and mine, other than the person itself"

  2022influential citation
• Mitigating Knowledge Imbalance in Ai-Advised Decision-Making Through Collaborative User Involvement

  2022cites this paper
• Understanding Decision Subjects' Fairness Perceptions and Retention in Repeated Interactions with AI-Based Decision Systems

  2022cites this paper
• How Does Predictive Information Affect Human Ethical Preferences?

  2022cites this paper
• An investigation of safe and near-optimal strategies for prevention of Covid-19 exposure using stochastic hybrid models and machine learning

  2022cites this paper
• Enhancing Fairness Perception – Towards Human-Centred AI and Personalized Explanations Understanding the Factors Influencing Laypeople’s Fairness Perceptions of Algorithmic Decisions

  2022cites this paper
• Toward a decision process of the best machine learning model for multi-stakeholders: a crowdsourcing survey method

  2022influential citation
• Development and validation of an instrument to measure undergraduate students’ attitudes toward the ethics of artificial intelligence (AT-EAI) and analysis of its difference by gender and experience of AI education

  2022cites this paper
• Exploring How Machine Learning Practitioners (Try To) Use Fairness Toolkits

  2022cites this paper
• Towards a multi-stakeholder value-based assessment framework for algorithmic systems

  2022cites this paper
• Explaining automated decision-making: a multinational study of the GDPR right to meaningful information

  2022cites this paper
• Method for Appropriating the Brief Implicit Association Test to Elicit Biases in Users

  2022cites this paper
• Towards a Science of Human-AI Decision Making: A Survey of Empirical Studies

  2021influential citation
• Investigating and Mitigating Biases in Crowdsourced Data

  2021cites this paper
• A survey on datasets for fairness‐aware machine learning

  2021cites this paper
• Fairness perceptions of algorithmic decision-making: A systematic review of the empirical literature

  2021cites this paper
• Understanding Diversity in Human-AI Data: What Cognitive Style Disaggregation Reveals

  2021cites this paper
• Measuring User Experience Inclusivity in Human-AI Interaction via Five User Problem-Solving Styles

  2021cites this paper
• From anecdote to evidence: the relationship between personality and need for cognition of developers

  2021cites this paper
• Impact of Explanation Techniques and Representations on Users Comprehension and Confidence in Explainable AI

  year unknowninfluential citation
• International Journal of Human - Computer Studies

  year unknowncites this paper