My Model is Unfair, Do People Even Care? Visual Design Affects Trust and Perceived Bias in Machine Learning
My Model is Unfair, Do People Even Care? Visual Design Affects Trust and Perceived Bias in Machine Learning
复制标题
我的模型不公平，人们关心吗？
DOI：
10.1109/tvcg.2023.3327192
复制
发表时间：
2023
影响因子：
5.2
通讯作者：
Bearfield, Cindy Xiong
中科院分区：
文献类型：
--
作者：
Gaba, Aimen;Kaufman, Zhanna;Cheung, Jason;Shvakel, Marie;Hall, Kyle Wm;Brun, Yuriy;Bearfield, Cindy Xiong
机器学习技术已经变得无处不在，但不幸的是，它经常表现出偏见。因此，不同的利益相关者需要与日常系统中使用机器学习模型进行交互并做出明智的决定。可视化技术可以支持利益相关者理解和评估模型的准确性和公平性之间的权衡。本文旨在经验性地回答“可视化设计选择是否会影响利益相关者对模型偏见、对模型的信任以及采用模型的意愿的感知？”通过对1500多名参与者进行的一系列受控众包实验，我们确定了人们在决定信任哪些模型时遵循的一套策略。我们的结果表明，男性和女性对公平和表现的优先顺序是不同的，视觉设计选择对优先顺序有很大影响。例如，女性比男性更信任更公平的模型，当用文字而不是条形图来解释公平时，参与者更看重公平，而且明确地告诉一个模型有偏见比展示过去有偏见的表现产生的影响更大。我们通过比较多种文本和视觉设计选择的效果来检验我们的结果的概括性，并对公平性、知觉和信任差异背后的认知机制提供了潜在的解释。我们的研究指导设计考虑，以支持未来为机器学习开发可视化系统的工作。
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.
登录
查看更多内容
影响因子：
8.4
作者：
Frederick, S
通讯作者：
Frederick, S
DOI：
10.1145/503376.503402
发表时间：
2002-04
期刊：
Proceedings of the SIGCHI Conference on Human Factors in Computing Systems
影响因子：
--
作者：
Jun Zheng;Elizabeth S. Veinott;Nathan D. Bos;J. Olson;G. Olson
通讯作者：
Jun Zheng;Elizabeth S. Veinott;Nathan D. Bos;J. Olson;G. Olson
不同程度的标题-可视化错位对信息的信任和回忆
DOI：
--
发表时间：
2019
期刊：
International Conference on Human Factors in Computing Systems
影响因子：
--
作者：
H. Kong;Zhicheng Liu;Karrie Karahalios
通讯作者：
Karrie Karahalios
适应性心理测量程序的比较模拟
DOI：
--
发表时间：
2009
期刊：
影响因子：
--
作者：
Stefanie Otto;S. Weinzierl
通讯作者：
S. Weinzierl
信息呈现对机器学习预测的公平性感知的影响
DOI：
--
发表时间：
2021
期刊：
International Conference on Human Factors in Computing Systems
影响因子：
--
作者：
Niels van Berkel;Jorge Gonçalves;D. Russo;S. Hosio;M. Skov
通讯作者：
M. Skov