[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-127231-en":3,"doc-seo-127231-105":30,"detail-sidebar-cat-0-en-105":92},{"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":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},127231,2336475104042,"Skyler","https://ap-avatar.wpscdn.com/avatar/22000c4c32af1715be0?x-image-process=image/resize,m_fixed,w_180,h_180&k=1786537525561427321",8,"Research & Report","Understanding Interaction with Machine Learning through a Thematic Analysis Coding Assistant: A User Study","Interactive Machine Learning (ML) enables non-experts to iteratively train and improve models, yet limited research explains how these users actually interact with such systems. This study uses thematic analysis as a practical lens, examining 20 participants interacting with TACA. Using interaction logs and semi-structured interviews, results show critical reflection, new thematic insights, and shifts in interpretative stance, alongside misconceptions about ML concepts and forms of personal blame. Design implications support clearer understanding and reflexive work practices.","CSCW197  \nUnderstanding Interaction with Machine Learning through a Thematic Analysis Coding Assistant: A User Study  \nFEDERICO MILANA, University College London, United Kingdom ENRICO COSTANZA, University College London, United Kingdom MIRCO MUSOLESI, University College London, United Kingdom AMID AYOBI, University College London, United Kingdom  \nInteractive Machine Learning (ML) enables users, including non-experts in ML, to iteratively train and improve ML models. However, limited research has been reported on how non-experts interact with these systems. Focusing on thematic analysis as a practical application, we report on a user study where 20 participants interacted with TACA, a functioning Interactive ML tool. Thematic analysis involves individual interpretation of ambiguous data, hence it is suited for and can benefit from the iterative customization of models supported by Interactive ML. Through a combination of interaction logs and semi-structured interviews, our findings revealed that, by using TACA, participants critically reflected on their analysis, gained new thematic insights, and adapted their interpretative stance. We also document misconceptions of ML concepts, positivist views, and personal blame for poor model performance. We then discuss how applications could be designed to improve the understanding of Interactive ML concepts and foster reflexive work practices.  \nCCS Concepts: • Human-centered computing → Interactive systems and tools; • Computing methodologies → Machine learning.  \nAdditional Key Words and Phrases: interactive machine learning, thematic analysis  \nACM Reference Format:  \nFederico Milana, Enrico Costanza, Mirco Musolesi, and Amid Ayobi. 2025. Understanding Interaction with Machine Learning through a Thematic Analysis Coding Assistant: A User Study. Proc. ACM Hum.-Comput.  \nInteract. 9, 2, Article CSCW197 (April 2025), 36 pages. [https://doi.org/10.1145/3711095](https://doi.org/10.1145/3711095)  \n1 INTRODUCTION  \nMachine learning (ML) has become ubiquitous in today’s digital landscape, finding application in various domains and industries, and a growing number of users are interacting with systems that are driven by sophisticated algorithms. Currently, most of these applications are based on models trained on large data sets, with Large Language Models being the most recent examples. The dependence of model performance on the size of the training set is widely identified as one of the limitations of ML [44] . As a response, there is growing interest in achieving high performance by customizing models trained on smaller data sets [17, 40, 47, 70] .  \nInteractive ML has been proposed as one approach to potentially achieve greater accuracy when training models on small data sets or on data that is ambiguous in nature [3] . Interactive ML involves the end-users in an iterative and incremental learning process and leverage human feedback to drive machine learning. Rapid iteration cycles of input, model updates and output allow the model to be fine-tuned incrementally by re-labeling misclassifications, labeling data points near decision boundaries or setting preferences and thresholds. This “human-in-the-loop” approach  \nAuthors’ addresses: Federico Milana, [federico.milana.18@ucl.ac.uk](federico.milana.18@ucl.ac.uk), University College London, 66-72 Gower Street, London, United Kingdom, WC1E 6EA; Enrico Costanza, [e.costanza@ucl.ac.uk](e.costanza@ucl.ac.uk), University College London, 66-72 Gower Street, London, United Kingdom; Mirco Musolesi, [m.musolesi@ucl.ac.uk](m.musolesi@ucl.ac.uk), University College London, London, United Kingdom; Amid Ayobi, [amid.ayobi@ucl.ac.uk](amid.ayobi@ucl.ac.uk), University College London, 66-72 Gower Street, London, United Kingdom.  \n© 2025 Copyright held by the owner/author(s) .  \nThis is the author’s version of the work. It is posted here for your personal use. Not for redistribution. The definitive Version of Record was published in Proceedings of the ACM","cbCaitW4WypRU3c9","https://ap.wps.com/l/cbCaitW4WypRU3c9","pdf",3012136,1,36,"English","en",105,"# Introduction\n## Interactive ML and customization\n## Research gap on non-experts\n## User study design and qualitative analysis (QDA)","[{\"question\":\"What system was evaluated in the study, and who used it?\",\"answer\":\"The study evaluated TACA, a functioning Interactive ML tool, with 20 participants interacting with it.\"},{\"question\":\"How does thematic analysis relate to interactive ML in this work?\",\"answer\":\"Thematic analysis matches Interactive ML because it involves interpreting ambiguous data, and iterative customization can refine interpretations through feedback loops.\"},{\"question\":\"What did participants gain and what issues emerged during interaction?\",\"answer\":\"Participants critically reflected on their analysis, gained new thematic insights, and adapted their interpretative stance. The study also documented misconceptions about ML concepts and personal blame for poor performance.\"}]","Understanding Interaction with Machine Learning through a Thematic Analysis Coding Assistant: A User Study | PDF",1785937650,91,{"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":87,"head_meta":89,"extra_data":91,"updated_unix":28},"understanding-interaction-with-machine-learning-through-a-thematic-analysis-coding-assistant-a-user-study","",{"@graph":36,"@context":86},[37,54,69],{"@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/understanding-interaction-with-machine-learning-through-a-thematic-analysis-coding-assistant-a-user-study/127231/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":23,"description":14,"dateModified":62,"datePublished":63,"encodingFormat":61,"isAccessibleForFree":64,"interactionStatistic":65},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":41,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-21","2026-08-05",true,{"@type":66,"interactionType":67,"userInteractionCount":20},"InteractionCounter",{"@type":68},"ViewAction",{"@type":70,"mainEntity":71},"FAQPage",[72,78,82],{"name":73,"@type":74,"acceptedAnswer":75},"What system was evaluated in the study, and who used it?","Question",{"text":76,"@type":77},"The study evaluated TACA, a functioning Interactive ML tool, with 20 participants interacting with it.","Answer",{"name":79,"@type":74,"acceptedAnswer":80},"How does thematic analysis relate to interactive ML in this work?",{"text":81,"@type":77},"Thematic analysis matches Interactive ML because it involves interpreting ambiguous data, and iterative customization can refine interpretations through feedback loops.",{"name":83,"@type":74,"acceptedAnswer":84},"What did participants gain and what issues emerged during interaction?",{"text":85,"@type":77},"Participants critically reflected on their analysis, gained new thematic insights, and adapted their interpretative stance. The study also documented misconceptions about ML concepts and personal blame for poor performance.","https://schema.org",{"og:url":52,"og:type":88,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":90,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":93},[94,98,102,106,111,116,121,124,129,132,136],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":95,"show_sort_weight":96,"slug":97},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":99,"show_sort_weight":100,"slug":101},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":103,"show_sort_weight":104,"slug":105},"Exam",70,"exam",{"id":107,"doc_module":4,"doc_module_name":46,"category_name":108,"show_sort_weight":109,"slug":110},5,"Comic",60,"comic",{"id":112,"doc_module":4,"doc_module_name":46,"category_name":113,"show_sort_weight":114,"slug":115},6,"Technology",50,"technology",{"id":117,"doc_module":4,"doc_module_name":46,"category_name":118,"show_sort_weight":119,"slug":120},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":122,"slug":123},30,"research-report",{"id":125,"doc_module":4,"doc_module_name":46,"category_name":126,"show_sort_weight":127,"slug":128},9,"Religion & Spirituality",20,"religion-spirituality",{"id":127,"doc_module":4,"doc_module_name":46,"category_name":130,"show_sort_weight":127,"slug":131},"World Cup","world-cup",{"id":133,"doc_module":4,"doc_module_name":46,"category_name":134,"show_sort_weight":133,"slug":135},10,"Lifestyle","lifestyle",{"id":137,"doc_module":4,"doc_module_name":46,"category_name":138,"show_sort_weight":107,"slug":139},19,"General","general"]