[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-seo-290733-105":3,"detail-sidebar-cat-0-en-105":81,"doc-detail-290733-en":131},{"code":4,"msg":5,"data":6},0,"ok",{"site_id":7,"language":8,"slug":9,"title":10,"keywords":11,"description":12,"schema_data":13,"social_meta":74,"head_meta":76,"extra_data":78,"updated_unix":80},105,"en","training-machine-learning-algorithms-for-automatic-facial-coding-the-role-of-emotional-facial-expressions-prototypicality","Training machine learning algorithms for automatic facial coding - The role of emotional facial expressions’ prototypicality","","Automatic facial coding (AFC) enables efficient analysis of emotional facial expressions by using machine learning to infer emotion categories from facial movements (Action Units). Contemporary AFC performs best for intense, prototypical expressions but is less accurate for nonprototypical and less intense ones. Because AFC models are often trained on standardized, prototypical expression inventories, prototypicality of training material may limit generalization. Models trained on highly prototypical standardized datasets dropped markedly when tested on unstandardized laboratory material, whereas training on unstandardized expressions preserved performance on standardized data. Findings highlight the training material’s prototypicality as a key determinant of AFC classification ability and support using more naturalistic facial expressions to improve robustness.",{"@graph":14,"@context":73},[15,34,56],{"@type":16,"itemListElement":17},"BreadcrumbList",[18,23,27,31],{"item":19,"name":20,"@type":21,"position":22},"https://docshare.wps.com","Home","ListItem",1,{"item":24,"name":25,"@type":21,"position":26},"https://docshare.wps.com/document/","Document",2,{"item":28,"name":29,"@type":21,"position":30},"https://docshare.wps.com/document/research-report/","Research & Report",3,{"item":32,"name":10,"@type":21,"position":33},"https://docshare.wps.com/document/training-machine-learning-algorithms-for-automatic-facial-coding-the-role-of-emotional-facial-expressions-prototypicality/290733/",4,{"url":32,"name":10,"@type":35,"image":36,"author":41,"headline":10,"publisher":44,"fileFormat":47,"inLanguage":8,"description":12,"dateModified":48,"datePublished":49,"encodingFormat":47,"isAccessibleForFree":50,"interactionStatistic":51},"DigitalDocument",{"url":37,"@type":38,"width":39,"height":40},"https://docshare.wps.com/thumbnails/training-machine-learning-algorithms-for-automatic-facial-coding-the-role-of-emotional-facial-expressions-prototypicality/290733.png","ImageObject",300,407,{"name":42,"@type":43},"Miles","Person",{"url":19,"name":45,"@type":46},"DocShare","Organization","application/pdf","2026-10-18","2026-09-17",true,{"@type":52,"interactionType":53,"userInteractionCount":55},"InteractionCounter",{"@type":54},"ViewAction",11,{"@type":57,"mainEntity":58},"FAQPage",[59,65,69],{"name":60,"@type":61,"acceptedAnswer":62},"What is automatic facial coding (AFC) and how does it work?","Question",{"text":63,"@type":64},"AFC is a machine-learning-based tool that infers emotion categories from facial movements, represented as Action Units, following the logic of FACS. It typically involves extracting AU features from images and mapping them to emotion categories.","Answer",{"name":66,"@type":61,"acceptedAnswer":67},"How does the prototypicality of training data affect AFC accuracy?",{"text":68,"@type":64},"Models trained on highly prototypical standardized datasets show a substantial accuracy drop when tested on unstandardized, laboratory-derived data. In contrast, models trained on unstandardized expressions maintain accuracy when tested on standardized datasets.",{"name":70,"@type":61,"acceptedAnswer":71},"Why is using more naturalistic facial expressions suggested for future AFC development?",{"text":72,"@type":64},"Because prototypicality strongly influences generalizability, incorporating more naturalistic facial expressions in training is expected to improve robustness and the ability to encode a wider range of emotional faces in research and naturalistic scenarios.","https://schema.org",{"og:url":32,"og:type":75,"og:title":10,"og:site_name":45,"og:description":12},"article",{"robots":77,"canonical":32},"index,follow",{"doc_id":79,"site_id":7},290733,1789642468,{"code":4,"msg":82,"data":83},"success",[84,88,92,96,101,106,111,115,120,123,127],{"id":22,"doc_module":4,"doc_module_name":25,"category_name":85,"show_sort_weight":86,"slug":87},"Story & Novel",90,"story-novel",{"id":26,"doc_module":4,"doc_module_name":25,"category_name":89,"show_sort_weight":90,"slug":91},"Literature",80,"literature",{"id":33,"doc_module":4,"doc_module_name":25,"category_name":93,"show_sort_weight":94,"slug":95},"Exam",70,"exam",{"id":97,"doc_module":4,"doc_module_name":25,"category_name":98,"show_sort_weight":99,"slug":100},5,"Comic",60,"comic",{"id":102,"doc_module":4,"doc_module_name":25,"category_name":103,"show_sort_weight":104,"slug":105},6,"Technology",50,"technology",{"id":107,"doc_module":4,"doc_module_name":25,"category_name":108,"show_sort_weight":109,"slug":110},7,"Healthcare",40,"healthcare",{"id":112,"doc_module":4,"doc_module_name":25,"category_name":29,"show_sort_weight":113,"slug":114},8,30,"research-report",{"id":116,"doc_module":4,"doc_module_name":25,"category_name":117,"show_sort_weight":118,"slug":119},9,"Religion & Spirituality",20,"religion-spirituality",{"id":118,"doc_module":4,"doc_module_name":25,"category_name":121,"show_sort_weight":118,"slug":122},"World Cup","world-cup",{"id":124,"doc_module":4,"doc_module_name":25,"category_name":125,"show_sort_weight":124,"slug":126},10,"Lifestyle","lifestyle",{"id":128,"doc_module":4,"doc_module_name":25,"category_name":129,"show_sort_weight":97,"slug":130},19,"General","general",{"code":4,"msg":82,"data":132},{"doc_id":79,"user_id":133,"nickname":42,"user_avatar":134,"doc_module":4,"category_id":112,"category_name":29,"doc_title":10,"doc_description":12,"doc_content":135,"file_id":136,"file_url":137,"file_type":138,"file_size":139,"view_count":55,"is_deleted":4,"is_public":22,"is_downloadable":22,"audit_status":22,"page_count":140,"language":141,"language_code":8,"site_id":7,"html_lang":8,"table_of_contents":142,"faqs":143,"seo_title":144,"seo_description":12,"update_tm":80,"read_time":109,"preview_page_count":4},13056703019404,"https://ap-avatar.wpscdn.com/davatar_29158cc5080c5b710cf443261637dec0","PLOS ONE  \nOPEN ACCESS  \nCitation: Bu¨denbender B, Ho¨fling TTA, Gerdes ABM, Alpers GW (2023) Training machine learning algorithms for automatic facial coding: The role of emotional facial expressions’ prototypicality. PLoSONE 18(2): e0281309 . [https://doi.org/10.1371/](https://doi.org/10.1371/)[ ](https://doi.org/10.1371/)[journal.pone.0281309](journal.pone.0281309)  \nEditor: Muhammad Fazal Ijaz, Sejong University, REPUBLIC OF KOREA  \nReceived: August 17, 2022  \nAccepted: January 20, 2023  \nPublished: February 10, 2023  \nCopyright: © 2023 Bu¨denbender et al. This is an open access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.  \nData Availability Statement: Data for the study are available at [https://madata.bib.uni-mannheim.de/id/](https://madata.bib.uni-mannheim.de/id/)[ ](https://madata.bib.uni-mannheim.de/id/)[eprint/327](eprint/327) [1] . 1. Ho¨fling TTA, Alpers GW, Bu¨denbender B, Gerdes ABM, Fo¨hl U. What’s in a face: Automatic facial coding of basic emotional expressions of untrained participants compared to trained actors [Data file] . University of Mannheim;  \n2020. doi:10.7801/327 The R code files are available from the data repository of the University of Mannheim ([https://madata.bib.uni-mannheim](https://madata.bib.uni-mannheim). de/408/); The repository additionally also has a doi: 10.7801/408 .  \nRESEARCH ARTICLE  \nTraining machine learning algorithms for automatic facial coding: The role of emotional facial expressions’ prototypicality  \nBj¨orn Bu¨denbender☯, Tim T. A. H¨ofling☯, Antje B. M. Gerdes, Georg W. Alpers * Department of Psychology, School of Social Sciences, University of Mannheim, Mannheim, Germany  \n☯ These authors contributed equally to this work.  \n* [alpers@mail.uni-mannheim.de](alpers@mail.uni-mannheim.de)  \nAbstract  \nAutomatic facial coding (AFC) is a promising new research tool to efficiently analyze emotional facial expressions. AFC is based on machine learning procedures to infer emotion categorization from facial movements (i.e. , Action Units) . State-of-the-art AFC accurately classifies intense and prototypical facial expressions, whereas it is less accurate for nonprototypical and less intense facial expressions. A potential reason might be that AFC is typically trained with standardized and prototypical facial expression inventories. Because AFC would be useful to analyze less prototypical research material as well, we set out to determine the role of prototypicality in the training material. We trained established machine learning algorithms either with standardized expressions from widely used research inventories or with unstandardized emotional facial expressions obtained in a typical laboratory setting and tested them on identical or cross-over material. All machine learning models’accuracies were comparable when trained and tested with held-out dataset from the same dataset (acc. = [83 .4% to 92 .5%]) . Strikingly, we found a substantial drop in accuracies for models trained with the highly prototypical standardized dataset when tested in the unstandardized dataset (acc. = [52 .8%; 69 .8%]) . However, when they were trained with unstandardized expressions and tested with standardized datasets, accuracies held up (acc. =[82 .7%; 92.5%]) . These findings demonstrate a strong impact of the training material’s prototypicality on AFC’s ability to classify emotional faces. Because AFC would be useful for analyzing emotional facial expressions in research or even naturalistic scenarios, future developments should include more naturalistic facial expressions for training. This approach will improve the generalizability of AFC to encode more naturalistic facial expressions and increase robustness for future applications of this promising technology.  \nIntroduction  \nAutomatic Facial Coding (AFC) is now ubiquitous and has ","cbCaij8hS5VJhELI","https://ap.wps.com/l/cbCaij8hS5VJhELI","pdf",1957141,16,"English","# Abstract\n# Introduction\n## Automatic Facial Coding (AFC) and FACS logic\n# AFC of standardized facial expressions","[{\"question\":\"What is automatic facial coding (AFC) and how does it work?\",\"answer\":\"AFC is a machine-learning-based tool that infers emotion categories from facial movements, represented as Action Units, following the logic of FACS. It typically involves extracting AU features from images and mapping them to emotion categories.\"},{\"question\":\"How does the prototypicality of training data affect AFC accuracy?\",\"answer\":\"Models trained on highly prototypical standardized datasets show a substantial accuracy drop when tested on unstandardized, laboratory-derived data. In contrast, models trained on unstandardized expressions maintain accuracy when tested on standardized datasets.\"},{\"question\":\"Why is using more naturalistic facial expressions suggested for future AFC development?\",\"answer\":\"Because prototypicality strongly influences generalizability, incorporating more naturalistic facial expressions in training is expected to improve robustness and the ability to encode a wider range of emotional faces in research and naturalistic scenarios.\"}]","Training machine learning algorithms for automatic facial coding - The role of emotional facial expressions’ prototypicality | PDF"]