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.
@article{Gaba23vis,
author = {Aimen Gaba and Zhanna Kaufman and Jason Cheung and Marie Shvakel and Kyle Wm Hall and Yuriy Brun and Cindy Xiong Bearfield},
title = {\href{http://people.cs.umass.edu/brun/pubs/pubs/Gaba23vis.pdf}{My Model is Unfair, Do People Even Care? {Visual} Design Affects Trust and Perceived Bias in Machine Learning}},
journal = {IEEE Transactions on Visualization and Computer Graphics (TVCG)},
venue = {TVCG},
year = {2024},
volume = {30},
number = {1},
pages = {327--337},
month = jan,
accept = {$\frac{133}{539} \approx 25\%$},
doi = {10.1109/TVCG.2023.3327192},
note = {Accepted as part of IEEE Visualization \& Visual Analytics (VIS) Conference, Melbourne, Australia, October 22--27, 2023.
\href{https://doi.org/10.1109/TVCG.2023.3327192}{DOI:
10.1109/TVCG.2023.3327192}, arXiv: \href{https://arxiv.org/abs/2308.03299}{abs/2308.03299}},
abstract = {<p>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.</p>},
fundedBy = {NSF IIS-2237585, NSF CCF-2210243, NSF CCF-1763423, Dolby},
}