[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-124763-en":3,"doc-seo-124763-105":30,"detail-sidebar-cat-0-en-105":95},{"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},124763,1649267921044,"Ava Thompson","https://us-avatar.wpscdn.com/avatar/1800007509477c92dfb?_k=1782875107921204101",8,"Research & Report","Recalibrating Machine Learning for Social Biases - Demonstrating a New Methodology through a Case Study","This thesis proposes a recalibration of machine learning systems for social biases to reduce harm caused by existing approaches. It prioritizes quality over quantity, accuracy over efficiency, representativeness over convenience, and situated thinking over universal thinking, using an alternative model-building process. Grounded in GLAM, the humanities, social sciences, and design, it examines how biases can be understood and communicated in a focused case study of gender-biased language within archival metadata. Using manually annotated data, the work trains and evaluates text classification models, showing that automation is possible for some bias types while conceptual subjectivity limits generalizability.","This thesis has been submitted in fulfilment of the requirements for a postgraduate degree (e. g. PhD, MPhil, DClinPsychol) at the University of Edinburgh. Please note the following terms and conditions of use:  \n This work is protected by copyright and other intellectual property rights, which are retained by the thesis author, unless otherwise stated.  \n A copy can be downloaded for personal non-commercial research or study, without prior permission or charge.  \n This thesis cannot be reproduced or quoted extensively from without first obtaining permission in writing from the author.  \n The content must not be changed in any way or sold commercially in any format or medium without the formal permission of the author.  \n When referring to this work, full bibliographic details including the author, title, awarding institution and date of the thesis must be given.  \nRecalibrating Machine Learning for Social Biases: Demonstrating a New Methodology through a Case Study Classifying Gender Biases in Archival  \nDocumentation  \nLucy Joan Havens  \nU  \nR  \nG  \nH  \nO  \nF  \nE  \nD  \nDoctor of Philosophy  \nInstitute for Language, Cognition and Computation School of Informatics  \nUniversity of Edinburgh  \nAbstract  \nThis thesis proposes a recalibration of Machine Learning for social biases to minimize harms from existing approaches and practices in the field. Prioritizing quality over quantity, accuracy over efficiency, representativeness over convenience, and situated thinking over universal thinking, the thesis demonstrates an alternative approach to creating Machine Learning models. Drawing on GLAM, the Humanities, the Social Sciences, and Design, the thesis focuses on understanding and communicating biases in a specific use case. 11,888 metadata descriptions from the University of Edinburgh Heritage Collections’ Archives catalog were manually annotated for gender biases and text classification models were then trained on the resulting dataset of 55,260 annotations. Evaluations of the models’ performance demonstrates that annotating gender biases can be automated; however, the subjectivity of bias as a concept complicates the generalizability of any one approach.  \nThe contributions are: (1) an interdisciplinary and participatory Bias-Aware Methodology, (2) a Taxonomy of Gendered and Gender Biased Language,(3) data annotated for gender biased language, (4) gender biased text classification models, and (5) a human-centered approach to model evaluation. The contributions have implications for Machine Learning, demonstrating how bias is inherent to all data and models; more specifically for Natural Language Processing, providing an annotation taxonomy, annotated datasets and classification models for analyzing gender biased language at scale; for the Gallery, Library, Archives, and Museum sector, offering guidance to institutions seeking to reconcile with histories of marginalizing communities through their documentation practices; and for historians, who utilize cultural heritage documentation to study and interpret the past. Through a real-world application of the Bias-Aware Methodology in a case study, the thesis illustrates the need to shift away from removing social biases and towards acknowledging them, creating data and models that surface the uncertainty and multiplicity characteristic of human societies.  \nLay Summary  \nExisting approaches to creating Machine Learning (ML) systems build harmful social biases, such as gender and racial biases, into the systems, through their data and models. Drawing on approaches from Galleries, Libraries, Archives, and Museums (GLAM); as well as the Humanities, the Social Sciences, and Design; I propose a new approach to creating ML systems that makes social biases in the systems visible. Research was undertaken for a specific use case: detecting gender biased language in the Archives catalog of the University of Edinburgh’s Heritage Collections. Creating a dataset of archival metadata descriptions","cbCaijiJCLOiKZyf","https://ap.wps.com/l/cbCaijiJCLOiKZyf","pdf",13586055,1,433,"English","en",105,"# Abstract\n## Contributions\n## Lay Summary\n## Implications","[{\"question\":\"What does the thesis propose to change about machine learning for social biases?\",\"answer\":\"It proposes recalibrating machine learning approaches to minimize harms from existing practices, emphasizing quality, accuracy, representativeness, and situated thinking.\"},{\"question\":\"How was the case study on gender biases conducted?\",\"answer\":\"Gender biases in archival metadata descriptions from the University of Edinburgh Heritage Collections were manually annotated, then machine learning text classification models were trained and evaluated on the resulting dataset.\"},{\"question\":\"What do the evaluations show about detecting gender-biased language?\",\"answer\":\"The models can automate detection for some types of gender biases, but the subjectivity of bias and variation across bias types limit complete automation and generalizability.\"},{\"question\":\"What broader implications does the thesis claim?\",\"answer\":\"It argues that bias is inherent to data and models, and it offers guidance for machine learning, GLAM institutions, and historians to acknowledge rather than remove social biases in documentation.\"}]","Recalibrating Machine Learning for Social Biases - Demonstrating a New Methodology through a Case Study | PDF",1785894366,1091,{"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":90,"head_meta":92,"extra_data":94,"updated_unix":28},"recalibrating-machine-learning-for-social-biases-demonstrating-a-new-methodology-through-a-case-study","",{"@graph":36,"@context":89},[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/recalibrating-machine-learning-for-social-biases-demonstrating-a-new-methodology-through-a-case-study/124763/",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",[71,77,81,85],{"name":72,"@type":73,"acceptedAnswer":74},"What does the thesis propose to change about machine learning for social biases?","Question",{"text":75,"@type":76},"It proposes recalibrating machine learning approaches to minimize harms from existing practices, emphasizing quality, accuracy, representativeness, and situated thinking.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How was the case study on gender biases conducted?",{"text":80,"@type":76},"Gender biases in archival metadata descriptions from the University of Edinburgh Heritage Collections were manually annotated, then machine learning text classification models were trained and evaluated on the resulting dataset.",{"name":82,"@type":73,"acceptedAnswer":83},"What do the evaluations show about detecting gender-biased language?",{"text":84,"@type":76},"The models can automate detection for some types of gender biases, but the subjectivity of bias and variation across bias types limit complete automation and generalizability.",{"name":86,"@type":73,"acceptedAnswer":87},"What broader implications does the thesis claim?",{"text":88,"@type":76},"It argues that bias is inherent to data and models, and it offers guidance for machine learning, GLAM institutions, and historians to acknowledge rather than remove social biases in documentation.","https://schema.org",{"og:url":52,"og:type":91,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":93,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":96},[97,101,105,109,114,119,124,127,132,135,139],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":98,"show_sort_weight":99,"slug":100},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":102,"show_sort_weight":103,"slug":104},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":106,"show_sort_weight":107,"slug":108},"Exam",70,"exam",{"id":110,"doc_module":4,"doc_module_name":46,"category_name":111,"show_sort_weight":112,"slug":113},5,"Comic",60,"comic",{"id":115,"doc_module":4,"doc_module_name":46,"category_name":116,"show_sort_weight":117,"slug":118},6,"Technology",50,"technology",{"id":120,"doc_module":4,"doc_module_name":46,"category_name":121,"show_sort_weight":122,"slug":123},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":125,"slug":126},30,"research-report",{"id":128,"doc_module":4,"doc_module_name":46,"category_name":129,"show_sort_weight":130,"slug":131},9,"Religion & Spirituality",20,"religion-spirituality",{"id":130,"doc_module":4,"doc_module_name":46,"category_name":133,"show_sort_weight":130,"slug":134},"World Cup","world-cup",{"id":136,"doc_module":4,"doc_module_name":46,"category_name":137,"show_sort_weight":136,"slug":138},10,"Lifestyle","lifestyle",{"id":140,"doc_module":4,"doc_module_name":46,"category_name":141,"show_sort_weight":110,"slug":142},19,"General","general"]