[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-125862-en":3,"doc-seo-125862-105":31,"detail-sidebar-cat-0-en-105":93},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":20,"is_deleted":4,"is_public":21,"is_downloadable":21,"audit_status":21,"page_count":22,"language":23,"language_code":24,"site_id":25,"html_lang":24,"table_of_contents":26,"faqs":27,"seo_title":28,"seo_description":14,"update_tm":29,"read_time":30},125862,1099523882367,"Hazel","https://ap-avatar.wpscdn.com/davatar_9964176cb1d06d4a9deccf72a44ae3dc",8,"Research & Report","My Model is Unfair - Visual Design Affects Trust and Perceived Bias in Machine Learning","Machine learning is widely used but often produces biased outcomes, prompting diverse stakeholders to weigh trade-offs when adopting model-driven decisions in everyday systems. The work studies whether visualization design choices change how people perceive model bias, trustworthiness, and willingness to adopt. Using controlled crowd-sourced experiments with 1,500+ participants, it identifies decision strategies, finds gender differences in valuing fairness versus performance, and shows visual and textual explanations can alter fairness perception and trust.","arXiv :2308 .03299v1 [ cs .HC] 7 Aug 2023  \nMy Model is Unfair, Do People Even Care?  \nVisual Design Affects Trust and Perceived Bias in Machine Learning  \nAimen Gaba⋆, Zhanna Kaufman⋆, Jason Cheung, Marie Shvakel, Kyle Wm. Hall, Yuriy Brun, and Cindy Xiong Bearfield  \nAbstract—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  \n1,500 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.  \nIndex Terms—machine learning, fairness, bias, trust, visual design, gender, human-subjects studies  \n1 INTRODUCTION  \nData-driven systems that use machine learning (ML) are ubiquitous intoday’s society, spanning high-impact domains such as healthcare [41], banking [60], hiring [65], and the criminal justice system [4] . Unfortunately, such systems can be unsafe and biased (e.g., racist or sexist), which erodes people’s trust. For example, IBM Watson recommended potentially fatal cancer treatments [63], cancer diagnosis systems have exhibited lower detection rates for people of color [88], software used by courts in setting bail have been found to have racial bias [4], and facial recognition systems routinely discriminate against women and people of color [13] . Such issues have led to legal bans of some types of ML systems [69, 70] . While extensive work focuses on reducing bias in ML algorithms [5, 27, 48, 74], such methods often result in compromises; for example, sacrificing system accuracy for fairness, or requiring more expensive data or computational resources, thereby necessitating human involvement and complex decision-making.  \nVisualization is one powerful strategy to inform users of such compromises [14, 36], but visualization design choices can profoundly affect how people reason [81], compare data values [24, 87], infer about people [35], draw causal conclusions [85], trust the data [20, 47, 53, 82], and perceive fairness [75, 78] . Therefore, practitioners who create visualizations to communicate ML model information must proceed cautiously with their design choices, as even without visualizationsthe way ML models are described can impact people’s trust in those models [89] and how they perceive model fairness [75] . As stakeholders with a variety of knowledge and experience use visualization to support reasoning about ML models [45], the visualization community must study the effects of visualization on how people reason about ML models, including perceptions of model fairness and trustworthiness.  \n⋆ Aimen Gaba and Zhanna Kaufman contributed equally to this work asco-first authors.  \n• Aimen Gaba, Zhanna Kaufman, Jason Cheung, Marie Shvakel, Yuriy Brun, and Cindy Xion","cbCaiaoioCVUTAiH","https://ap.wps.com/l/cbCaiaoioCVUTAiH","pdf",4342211,7,1,11,"English","en",105,"# Introduction\n## Bias in machine learning systems\n## Visualization and stakeholder reasoning\n# Research approach\n## Trust-game framework\n## Controlled crowd-sourced experiments\n# Findings overview\n## Strategies for trusting models\n## Effects of visual and textual design on trust and perceived bias","[{\"question\":\"What question does the paper aim to answer about visualization?\",\"answer\":\"It empirically tests whether visualization design choices affect a stakeholder’s perception of model bias, trust, and willingness to adopt machine learning models.\"},{\"question\":\"How did the researchers measure trust and perceived fairness?\",\"answer\":\"They used a trust-game framework where participants choose between investment models labeled as fair or biased, and investment frequency served as a proxy for trust.\"},{\"question\":\"What key results relate visual design to trust and bias perception?\",\"answer\":\"Visualization and explanation formats significantly influence how people prioritize fairness versus performance, with gender differences in these priorities and stronger impact when told explicitly a model is biased.\"}]","My Model is Unfair - Visual Design Affects Trust and Perceived Bias in Machine Learning | PDF",1785901638,28,{"code":4,"msg":32,"data":33},"ok",{"site_id":25,"language":24,"slug":34,"title":13,"keywords":35,"description":14,"schema_data":36,"social_meta":88,"head_meta":90,"extra_data":92,"updated_unix":29},"my-model-is-unfair-visual-design-affects-trust-and-perceived-bias-in-machine-learning","",{"@graph":37,"@context":87},[38,55,70],{"@type":39,"itemListElement":40},"BreadcrumbList",[41,45,49,52],{"item":42,"name":43,"@type":44,"position":21},"https://docshare.wps.com","Home","ListItem",{"item":46,"name":47,"@type":44,"position":48},"https://docshare.wps.com/document/","Document",2,{"item":50,"name":12,"@type":44,"position":51},"https://docshare.wps.com/document/research-report/",3,{"item":53,"name":13,"@type":44,"position":54},"https://docshare.wps.com/document/my-model-is-unfair-visual-design-affects-trust-and-perceived-bias-in-machine-learning/125862/",4,{"url":53,"name":13,"@type":56,"author":57,"headline":13,"publisher":59,"fileFormat":62,"inLanguage":24,"description":14,"dateModified":63,"datePublished":64,"encodingFormat":62,"isAccessibleForFree":65,"interactionStatistic":66},"DigitalDocument",{"name":9,"@type":58},"Person",{"url":42,"name":60,"@type":61},"DocShare","Organization","application/pdf","2026-08-24","2026-08-05",true,{"@type":67,"interactionType":68,"userInteractionCount":20},"InteractionCounter",{"@type":69},"ViewAction",{"@type":71,"mainEntity":72},"FAQPage",[73,79,83],{"name":74,"@type":75,"acceptedAnswer":76},"What question does the paper aim to answer about visualization?","Question",{"text":77,"@type":78},"It empirically tests whether visualization design choices affect a stakeholder’s perception of model bias, trust, and willingness to adopt machine learning models.","Answer",{"name":80,"@type":75,"acceptedAnswer":81},"How did the researchers measure trust and perceived fairness?",{"text":82,"@type":78},"They used a trust-game framework where participants choose between investment models labeled as fair or biased, and investment frequency served as a proxy for trust.",{"name":84,"@type":75,"acceptedAnswer":85},"What key results relate visual design to trust and bias perception?",{"text":86,"@type":78},"Visualization and explanation formats significantly influence how people prioritize fairness versus performance, with gender differences in these priorities and stronger impact when told explicitly a model is biased.","https://schema.org",{"og:url":53,"og:type":89,"og:title":13,"og:site_name":60,"og:description":14},"article",{"robots":91,"canonical":53},"index,follow",{"doc_id":7,"site_id":25},{"code":4,"msg":5,"data":94},[95,99,103,107,112,117,121,124,129,132,136],{"id":21,"doc_module":4,"doc_module_name":47,"category_name":96,"show_sort_weight":97,"slug":98},"Story & Novel",90,"story-novel",{"id":48,"doc_module":4,"doc_module_name":47,"category_name":100,"show_sort_weight":101,"slug":102},"Literature",80,"literature",{"id":54,"doc_module":4,"doc_module_name":47,"category_name":104,"show_sort_weight":105,"slug":106},"Exam",70,"exam",{"id":108,"doc_module":4,"doc_module_name":47,"category_name":109,"show_sort_weight":110,"slug":111},5,"Comic",60,"comic",{"id":113,"doc_module":4,"doc_module_name":47,"category_name":114,"show_sort_weight":115,"slug":116},6,"Technology",50,"technology",{"id":20,"doc_module":4,"doc_module_name":47,"category_name":118,"show_sort_weight":119,"slug":120},"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":47,"category_name":12,"show_sort_weight":122,"slug":123},30,"research-report",{"id":125,"doc_module":4,"doc_module_name":47,"category_name":126,"show_sort_weight":127,"slug":128},9,"Religion & Spirituality",20,"religion-spirituality",{"id":127,"doc_module":4,"doc_module_name":47,"category_name":130,"show_sort_weight":127,"slug":131},"World Cup","world-cup",{"id":133,"doc_module":4,"doc_module_name":47,"category_name":134,"show_sort_weight":133,"slug":135},10,"Lifestyle","lifestyle",{"id":137,"doc_module":4,"doc_module_name":47,"category_name":138,"show_sort_weight":108,"slug":139},19,"General","general"]