[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-125408-en":3,"doc-seo-125408-105":30,"detail-sidebar-cat-0-en-105":91},{"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":4,"is_deleted":4,"is_public":20,"is_downloadable":20,"audit_status":20,"page_count":21,"language":22,"language_code":23,"site_id":24,"html_lang":23,"table_of_contents":25,"faqs":26,"seo_title":27,"seo_description":14,"update_tm":28,"read_time":29},125408,1374391974564,"Clementine","https://ap-avatar.wpscdn.com/avatar/14000253aa45c000a9e?x-image-process=image/resize,m_fixed,w_180,h_180&k=1779874745381141002",8,"Research & Report","Practitioners and Bias in Machine Learning - A Study","Increasing adoption of machine learning creates ethical risks, especially around algorithmic bias. This study examines how ML practitioners with limited bias experience define bias, choose bias detection measures, and apply mitigation methods in practice. Using a take-home task, exercises, and interviews with 22 participants, researchers identify five themes covering bias sources, metric selection, detection, mitigation, and ethics. Participants often face conflicts between fairness definitions, metric context, bias persistence in real data, performance trade-offs, and reliance on personal perspectives. Even with mitigation techniques, bias cannot be fully eliminated due to oversimplified modeling assumptions.","Practitioners and Bias in Machine Learning: A Study  \nROBERT CINCA and ENRICO COSTANZA, University College London, London, United Kingdom of Great Britain and Northern Ireland  \nMIRCO MUSOLESI, University College London, London, United Kingdom of Great Britain and Northern Ireland and University of Bologna, Bologna, Italy  \n\n| The increasing adoption of machine learning (ML) raises ethical concerns, particularly regarding bias. This study explores how ML practitioners with limited experience in bias understand and apply bias definitions, detection measures, and mitigation methods. Through a take-home task, exercises, and interviews with 22 participants, we identified five key themes: sources of bias, selecting bias metrics, detecting bias, mitigating bias, and ethical considerations. Participants faced unresolved conflicts, such as applying fairness definitions in practice, selecting context-dependent bias metrics, addressing real-world biases, balancing model performance with bias mitigation, and relying on personal perspectives over data-driven metrics. While bias mitigation techniques helped identify biases in two datasets, participants could not fully eliminate bias, citing the oversimplification of complex processes into models with limited variables. We propose designing bias detection tools that encourage practitioners to focus on the underlying assumptions and integrating bias concepts into ML practices, such as using a harmonic mean-based approach, akin to the F1 score, to balance bias and accuracy.\u003Cbr>CCS Concepts: • Human-centered computing ! Empirical studies inHCI; • Computing methodologies! Machine learning; • Social and professional topics ! Computing education;\u003Cbr>Additional Key Words and Phrases: ML Bias, Operationalizing Bias, machine learning, machine learning practitioners, interview study\u003Cbr>ACM Reference format:\u003Cbr>Robert Cinca, Enrico Costanza, and Mirco Musolesi. 2025. Practitioners and Bias in Machine Learning: A Study. ACM Trans. Interact. Intell. Syst. 15, 2, Article 12 (June 2025), 28 pages.\u003Cbr>[https://doi.org/10.1145/3733838](https://doi.org/10.1145/3733838) |\n| --- |\n| 1 Introduction\u003Cbr>Machine learning (ML) is being applied to an increasing number of diverse applications, such as loan applications, diagnosing disease, crime prevention, facial recognition, and language translation [51] . However, the expanding application of ML across various domains raises serious ethical |\n\nThis work was supported by the UK Engineering and Physical Sciences Research Council (EPSRC) grant EP/R513143/1 for the University College London Interaction Centre (UCLIC) . Our study was approved by the UCLIC Ethics Committee (UCLIC_2022_004_Costanza) .  \nAuthors’ Contact Information: Robert Cinca (corresponding author), University College London, London, United Kingdom of Great Britain and Northern Ireland; e-mail: [robert.cinca.14@ucl.ac.uk](robert.cinca.14@ucl.ac.uk); Enrico Costanza, University College London, London, United Kingdom of Great Britain and Northern Ireland; e-mail: [e.costanza@ucl.ac.uk](e.costanza@ucl.ac.uk); Mirco Musolesi, University College London, London, United Kingdom of Great Britain and Northern Ireland and University of Bologna, Bologna, Italy; [e-mail: m.musolesi@ucl.ac.uk](e-mail: m.musolesi@ucl.ac.uk).  \nThis work is licensed under Creative Commons Attribution International 4 .0 .  \n© 2025 Copyright held by the owner/author(s) .  \nACM 2160-6463/2025/6-ART12  \n[https://doi.org/10.1145/3733838](https://doi.org/10.1145/3733838)  \nACM Transactions on Interactive Intelligent Systems, Vol. 15, No. 2, Article 12 . Publication date: June 2025 .  \n12:2 R. Cinca et al.  \nconcerns and challenges related to bias. Certain fields, such as healthcare [75] and crime prevention [1], are particularly at risk of discrimination based on protected characteristics. Examples of biased outcomes include predicting a criminal’s re-offending probability while discriminating based on race [1], how search engine results ","cbCaiimnYh7Uld9z","https://ap.wps.com/l/cbCaiimnYh7Uld9z","pdf",8847837,1,28,"English","en",105,"# Introduction\n## Background: Bias risks in ML applications\n## Study goal and target participants\n# Research Design\n## Take-home task and exercises\n## Interviews and qualitative analysis\n# Key Findings\n## Sources of bias\n## Selecting bias metrics\n## Detecting bias\n## Mitigating bias\n## Ethical considerations\n# Discussion and Implications\n## Limits of mitigation in practice\n## Proposed bias detection tool approach","[{\"question\":\"What does the study investigate about machine learning practitioners and bias?\",\"answer\":\"The study examines how practitioners with limited experience in bias understand bias definitions, detect bias using measures, and apply mitigation methods during ML development.\"},{\"question\":\"How was the study conducted?\",\"answer\":\"Researchers used a take-home task, structured exercises, and follow-up semi-structured interviews with 22 participants.\"},{\"question\":\"What challenges did participants face when applying bias mitigation?\",\"answer\":\"Participants struggled with conflicts between fairness definitions and practice, context-dependent metric choices, real-world bias complexities, performance–mitigation trade-offs, and overreliance on personal perspectives rather than purely data-driven metrics.\"}]","Practitioners and Bias in Machine Learning - A Study | PDF",1785898737,71,{"code":4,"msg":31,"data":32},"ok",{"site_id":24,"language":23,"slug":33,"title":13,"keywords":34,"description":14,"schema_data":35,"social_meta":86,"head_meta":88,"extra_data":90,"updated_unix":28},"practitioners-and-bias-in-machine-learning-a-study","",{"@graph":36,"@context":85},[37,54,68],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,48,51],{"item":41,"name":42,"@type":43,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":47},"https://docshare.wps.com/document/","Document",2,{"item":49,"name":12,"@type":43,"position":50},"https://docshare.wps.com/document/research-report/",3,{"item":52,"name":13,"@type":43,"position":53},"https://docshare.wps.com/document/practitioners-and-bias-in-machine-learning-a-study/125408/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":23,"description":14,"dateModified":62,"datePublished":62,"encodingFormat":61,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":41,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-05",true,{"@type":65,"interactionType":66,"userInteractionCount":4},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"What does the study investigate about machine learning practitioners and bias?","Question",{"text":75,"@type":76},"The study examines how practitioners with limited experience in bias understand bias definitions, detect bias using measures, and apply mitigation methods during ML development.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How was the study conducted?",{"text":80,"@type":76},"Researchers used a take-home task, structured exercises, and follow-up semi-structured interviews with 22 participants.",{"name":82,"@type":73,"acceptedAnswer":83},"What challenges did participants face when applying bias mitigation?",{"text":84,"@type":76},"Participants struggled with conflicts between fairness definitions and practice, context-dependent metric choices, real-world bias complexities, performance–mitigation trade-offs, and overreliance on personal perspectives rather than purely data-driven metrics.","https://schema.org",{"og:url":52,"og:type":87,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":89,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":92},[93,97,101,105,110,115,120,123,128,131,135],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":102,"show_sort_weight":103,"slug":104},"Exam",70,"exam",{"id":106,"doc_module":4,"doc_module_name":46,"category_name":107,"show_sort_weight":108,"slug":109},5,"Comic",60,"comic",{"id":111,"doc_module":4,"doc_module_name":46,"category_name":112,"show_sort_weight":113,"slug":114},6,"Technology",50,"technology",{"id":116,"doc_module":4,"doc_module_name":46,"category_name":117,"show_sort_weight":118,"slug":119},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":121,"slug":122},30,"research-report",{"id":124,"doc_module":4,"doc_module_name":46,"category_name":125,"show_sort_weight":126,"slug":127},9,"Religion & Spirituality",20,"religion-spirituality",{"id":126,"doc_module":4,"doc_module_name":46,"category_name":129,"show_sort_weight":126,"slug":130},"World Cup","world-cup",{"id":132,"doc_module":4,"doc_module_name":46,"category_name":133,"show_sort_weight":132,"slug":134},10,"Lifestyle","lifestyle",{"id":136,"doc_module":4,"doc_module_name":46,"category_name":137,"show_sort_weight":106,"slug":138},19,"General","general"]