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

Machine learning technology has become ubiquitous, but, unfortunately, often exhibits bias. As a consequence, disparate stakeholders need to interact with and make informed decisions about using machine learning models in everyday systems. Visualization technology can support stakeholders in underst...

Full description

Saved in:
Bibliographic Details
Published in:IEEE transactions on visualization and computer graphics 2024-01, Vol.30 (1), p.327-337
Main Authors: Gaba, Aimen, Kaufman, Zhanna, Cheung, Jason, Shvakel, Marie, Hall, Kyle Wm, Brun, Yuriy, Bearfield, Cindy Xiong
Format: Article
Language:English
Subjects:
Analytical models
Bars
Bias
Computational modeling
Computer Graphics
Data models
fairness
Female
Games
gender
human-subjects studies
Humans
Investment
Machine Learning
Male
Perception
Surveys and Questionnaires
trust
Trust - psychology
visual design
Visualization
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Machine learning technology has become ubiquitous, but, unfortunately, often exhibits bias. As a consequence, disparate stakeholders need to interact with and make informed decisions about using machine learning models in everyday systems. Visualization technology can support stakeholders in understanding and evaluating trade-offs between, for example, accuracy and fairness of models. This paper aims to empirically answer "Can visualization design choices affect a stakeholder's perception of model bias, trust in a model, and willingness to adopt a model?" Through a series of controlled, crowd-sourced experiments with more than 1,500 participants, we identify a set of strategies people follow in deciding which models to trust. Our results show that men and women prioritize fairness and performance differently and that visual design choices significantly affect that prioritization. For example, women trust fairer models more often than men do, participants value fairness more when it is explained using text than as a bar chart, and being explicitly told a model is biased has a bigger impact than showing past biased performance. We test the generalizability of our results by comparing the effect of multiple textual and visual design choices and offer potential explanations of the cognitive mechanisms behind the difference in fairness perception and trust. Our research guides design considerations to support future work developing visualization systems for machine learning.
ISSN:1077-2626
1941-0506
DOI:10.1109/TVCG.2023.3327192