[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-122343-en":3,"doc-seo-122343-105":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},122343,2336464648746,"Skyler","https://ap-avatar.wpscdn.com/davatar_276721f389ce27ea32af1340a28f341c",8,"Research & Report","From Canvas to Code - A Machine Learning Exploration of Art History Using the Met’s Open Access Data","This thesis examines how machine learning can leverage textual metadata in the Metropolitan Museum of Art’s Open Access Collection, reflecting the growing overlap between artificial intelligence and digital humanities research. Drawing on 480,000+ collection records, the work applies unsupervised clustering (K-Modes, K-Means, HDBSCAN), supervised modeling (Random Forest), and association analysis to build a recommendation system. Findings show clustering groups artworks effectively using numeric and categorical attributes, while supervised prediction is more limited for sensitive features. The study identifies attribute-linked rules and demonstrates museum-database recommendation potential.","FROM CANVAS TO CODE: A MACHINE LEARNING EXPLORATION OF ART HISTORY  \nUSING THE MET’S OPEN ACCESS DATA  \nCharlotte Stinson  \nPlan II Honors  \nThe University of Texas at Austin  \nMay 2025  \nAngela Beasley  \nDepartment of Computer Science  \nSupervising Professor  \nAnn Collins Johns, Ph.D.  \nDepartment ofArt History  \nSecond Reader  \n2  \nAbstract  \nAuthor: Charlotte Stinson  \nTitle: From Canvas to Code: A Machine Learning Exploration ofArt History Using the Met’s Open Access Data  \nSupervising Professor: Angela Beasley  \nThis thesis explores how machine learning can be applied to the textual metadata in the Metropolitan Museum of Art’s Open Access Collection, motivated by the growing intersection between artificial intelligence and the digital humanities. Using over 480,000 records from the Met’s collection, I applied unsupervised clustering techniques (K-Modes, K-Means, HDBSCAN), supervised learning algorithms (Random Forest), and association analysis to create a recommendation system. The results revealed that clustering could effectively group artwork based on both numeric and categorical data, while supervised models had a more limited effectiveness in predicting features such as the artist’s gender. Association analysis identified rules related to artistic attributes, which was used to create a recommendation system that demonstrated the potential for similar systems in museum databases. There are identifiable trends in the Met’s open access collection that benefit from being found by a machine learning model. This shows the overall potential for incorporating artificial intelligence tools into art history research, and fits more broadly into the wider conversation about the feasibility of machine learning research to collaborate with the digital humanities.  \n3  \nAcknowledgements  \nTo my supervisor and second reader for supporting me through this process. Their expertise and advice were crucial in shaping my thesis.  \nTo my parents, sister, and grandmother for their love and encouragement.  \nTo my cat, Olive, for being my writing buddy and providing support by lounging on my keyboard.  \n4  \nTable Of Contents  \nIntroduction....................................................................................................................................5  \nLiterature Review.......................................................................................................................... 7  \nCross-Disciplinary Challenges within the Digital Humanities.................................................. 7  \nComputer Vision in Art History............................................................................................... 10  \nMetadata Analysis in Art History............................................................................................ 11  \nRecommender Systems............................................................................................................ 13  \nMethods.........................................................................................................................................17  \nDataset...................................................................................................................................... 17  \nOverview and Terminology..................................................................................................... 18  \nA Note on AI Generated Code.................................................................................................20  \nAlgorithm Analysis...................................................................................................................... 22  \nData Exploration and Cleaning................................................................................................22  \nKModes and K-means Clustering............................................................................................ 31  \nHDBSCAN........................................................................................","cbCaibhpaR7SlmQC","https://ap.wps.com/l/cbCaibhpaR7SlmQC","pdf",2242135,1,61,"English","en",105,"# Introduction\n## Literature Review\n## Cross-Disciplinary Challenges within the Digital Humanities\n## Computer Vision in Art History\n## Metadata Analysis in Art History\n## Recommender Systems\n# Methods\n## Dataset\n## Overview and Terminology\n## A Note on AI Generated Code\n## Algorithm Analysis\n## Data Exploration and Cleaning\n## KModes and K-means Clustering\n## HDBSCAN\n## Supervised Learning\n## Association Analysis\n## Recommender System\n# Conclusion\n# Works Cited\n# Biography","[{\"question\":\"What dataset and data type does the thesis use for the machine learning work?\",\"answer\":\"It uses over 480,000 records from the Met’s Open Access Collection, focusing on textual metadata to analyze artwork attributes and patterns.\"},{\"question\":\"Which machine learning methods are applied to the Met’s metadata?\",\"answer\":\"The thesis applies unsupervised clustering (K-Modes, K-Means, HDBSCAN), supervised learning with Random Forest, and association analysis to extract rules and support recommendations.\"},{\"question\":\"What do the results suggest about clustering, prediction, and recommendation in museum databases?\",\"answer\":\"Clustering can effectively group artworks using numeric and categorical data, while supervised models show more limited effectiveness for predicting certain features such as an artist’s gender. Association analysis produces attribute-related rules that support a recommendation system, demonstrating feasibility for similar systems in museum contexts.\"}]","From Canvas to Code - A Machine Learning Exploration of Art History Using the Met’s Open Access Data | PDF",1785810126,154,{"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},"from-canvas-to-code-a-machine-learning-exploration-of-art-history-using-the-mets-open-access-data","",{"@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/from-canvas-to-code-a-machine-learning-exploration-of-art-history-using-the-mets-open-access-data/122343/",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","2026-08-04",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 dataset and data type does the thesis use for the machine learning work?","Question",{"text":75,"@type":76},"It uses over 480,000 records from the Met’s Open Access Collection, focusing on textual metadata to analyze artwork attributes and patterns.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"Which machine learning methods are applied to the Met’s metadata?",{"text":80,"@type":76},"The thesis applies unsupervised clustering (K-Modes, K-Means, HDBSCAN), supervised learning with Random Forest, and association analysis to extract rules and support recommendations.",{"name":82,"@type":73,"acceptedAnswer":83},"What do the results suggest about clustering, prediction, and recommendation in museum databases?",{"text":84,"@type":76},"Clustering can effectively group artworks using numeric and categorical data, while supervised models show more limited effectiveness for predicting certain features such as an artist’s gender. Association analysis produces attribute-related rules that support a recommendation system, demonstrating feasibility for similar systems in museum contexts.","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"]