[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-126468-en":3,"doc-seo-126468-105":31,"detail-sidebar-cat-0-en-105":93},{"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":21,"is_downloadable":21,"audit_status":21,"page_count":22,"language":23,"language_code":24,"site_id":25,"html_lang":24,"table_of_contents":26,"faqs":27,"seo_title":28,"seo_description":14,"update_tm":29,"read_time":30},126468,962084925290,"Ophelia","https://ap-avatar.wpscdn.com/davatar_085a072bc5b1113ac321206ff7593b45",8,"Research & Report","Predicting Humanoid Robots Scariness Using Machine Learning on Facial Features - Master’s thesis","This master’s thesis predicts the scariness of humanoid robot faces using machine learning, examining how facial design parameters shape emotional responses in human-robot interaction. It uses two datasets drawn from the Anthropomorphic roBOT (ABOT) Database, including 202 robot face images encoded with 21 facial features and a second dataset containing emotional responses and participant demographics. After preprocessing and exploratory analysis, the study trains Decision Trees, Logistic Regression, SVM, and XGBoost, highlighting key facial features linked to scariness and improving performance by addressing class imbalance. It further analyzes demographic effects and provides design recommendations for manufacturers to reduce fear responses while noting constraints from dataset size and currency.","Master’s Programme in Information & Service Management  \nPREDICTING HUMANOID ROBOTSCARINESS USING MACHINE LEARNING ON FACIAL FEATURES  \nHuyen Pham  \nMaster’s thesis 2025  \nCopyright ©2025 Huyen Pham  \n\n| Author Huyen Pham |\n| --- |\n| Title of thesis Predicting Humanoid Robot Scariness Using Machine Learning on Facial Features |\n| Programme Information & Service Management |\n| Major Business Analytics |\n| Thesis supervisor Associate Professor Yong Liu |\n| Date 30.07.2025 Number of pages 88 Language English |\n| Abstract\u003Cbr>This thesis aims to predict the scariness of humanoid robot faces using machine learning (ML), focusing on the interplay between facial design and emotional responses in human-robot interaction (HRI) . The study employs two datasets, one from Jiajun Sun and the other from Kim et al. (2022), both of which are derived from the Anthropomorphic roBOT (ABOT) Database. The Jiajun Sun dataset comprises 202 robot faces encoded with 21 facial features, while the Kim et al. dataset includes emotional response data and participants' demographic details for the same 202 robot face images. The research identifies key facial features that influence scariness perceptions through preprocessing, exploratory data analysis, and the application of ML models: Decision Trees, Logistic Regression, SVM, and XGBoost. The findings reveal significant correlations between certain facial features and scariness, with models achieving robust predictive performance after addressing class imbalances. Additionally, the study examines how demographic factors affect scariness perceptions, providing actionable design recommendations for robot manufacturers to minimize fear responses. Despite limitations due to the dataset size and outdated data, this research enhances the understanding of HRI and offers practical guidelines for designing less intimidating robots. |\n| Keywords: Human-robot interaction, scariness prediction, machine learning, robot facial design, uncanny valley, facial features, ABOT Database. |\n\nTable of contents  \nPreface and Acknowledgements ..............................................................................................7  \nPreface and acknowledgments.................................................................................................7  \nSymbols and abbreviations ..................................................................................................... 8  \nSymbols ............................................................................................................................... 8  \nOperators ............................................................................................................................. 8  \nAbbreviations ...................................................................................................................... 8  \n1 Introduction..................................................................................................................... 9  \n1.1 Background and Motivation .................................................................................... 9  \n1.2 Research Objectives and Questions ......................................................................... 9  \n1.2.1 Research Problem................................................................................................. 9  \n1.2.2 Research Questions .........................................................................................10  \n1.2.3 Goals of the Research ......................................................................................10  \n1.3 The scope and limits of the study, along with the main concepts involved ........... 11  \n1.4 Structure of the thesis ............................................................................................. 12  \n2 Literature review ............................................................................................................ 13  \n2.1 Significance of Humanoid Robot Facial Design in Shaping H","cbCaiixiZhq8lQVF","https://ap.wps.com/l/cbCaiixiZhq8lQVF","pdf",3055264,9,1,88,"English","en",105,"# Preface and Acknowledgements\n# Symbols and abbreviations\n# 1 Introduction\n## Background and Motivation\n## Research Objectives and Questions\n## Scope and limits of the study\n## Structure of the thesis\n# 2 Literature review\n## Significance of Humanoid Robot Facial Design in Shaping HRI\n## The Uncanny Valley Hypothesis\n## The Role of Facial Expressions in Emotional Conveyance\n## Mitigating Scariness in Humanoid Robot Faces\n## Predictive Modeling of Scariness in Humanoid Robot Faces\n## Introduction to Machine Learning and Its Application in Image-Based Prediction\n## Thesis’s Contribution\n# 3 Data collection","[{\"question\":\"What is the main goal of the thesis?\",\"answer\":\"The thesis aims to predict how scary humanoid robot faces appear, using machine learning informed by facial design features and human emotional responses in HRI.\"},{\"question\":\"Which datasets are used in the scariness prediction study?\",\"answer\":\"It uses two datasets derived from the Anthropomorphic roBOT (ABOT) Database: one provides 202 robot face images encoded with 21 facial features, and the other provides emotional response data plus participant demographics for the same 202 images.\"},{\"question\":\"Which machine learning models are applied, and how are performance issues handled?\",\"answer\":\"The study applies Decision Trees, Logistic Regression, SVM, and XGBoost. It improves robustness by addressing class imbalances during modeling.\"}]","Predicting Humanoid Robots Scariness Using Machine Learning on Facial Features - Master’s thesis | PDF",1785905213,222,{"code":4,"msg":32,"data":33},"ok",{"site_id":25,"language":24,"slug":34,"title":13,"keywords":35,"description":14,"schema_data":36,"social_meta":88,"head_meta":90,"extra_data":92,"updated_unix":29},"predicting-humanoid-robots-scariness-using-machine-learning-on-facial-features-masters-thesis","",{"@graph":37,"@context":87},[38,55,70],{"@type":39,"itemListElement":40},"BreadcrumbList",[41,45,49,52],{"item":42,"name":43,"@type":44,"position":21},"https://docshare.wps.com","Home","ListItem",{"item":46,"name":47,"@type":44,"position":48},"https://docshare.wps.com/document/","Document",2,{"item":50,"name":12,"@type":44,"position":51},"https://docshare.wps.com/document/research-report/",3,{"item":53,"name":13,"@type":44,"position":54},"https://docshare.wps.com/document/predicting-humanoid-robots-scariness-using-machine-learning-on-facial-features-masters-thesis/126468/",4,{"url":53,"name":13,"@type":56,"author":57,"headline":13,"publisher":59,"fileFormat":62,"inLanguage":24,"description":14,"dateModified":63,"datePublished":64,"encodingFormat":62,"isAccessibleForFree":65,"interactionStatistic":66},"DigitalDocument",{"name":9,"@type":58},"Person",{"url":42,"name":60,"@type":61},"DocShare","Organization","application/pdf","2026-08-24","2026-08-05",true,{"@type":67,"interactionType":68,"userInteractionCount":20},"InteractionCounter",{"@type":69},"ViewAction",{"@type":71,"mainEntity":72},"FAQPage",[73,79,83],{"name":74,"@type":75,"acceptedAnswer":76},"What is the main goal of the thesis?","Question",{"text":77,"@type":78},"The thesis aims to predict how scary humanoid robot faces appear, using machine learning informed by facial design features and human emotional responses in HRI.","Answer",{"name":80,"@type":75,"acceptedAnswer":81},"Which datasets are used in the scariness prediction study?",{"text":82,"@type":78},"It uses two datasets derived from the Anthropomorphic roBOT (ABOT) Database: one provides 202 robot face images encoded with 21 facial features, and the other provides emotional response data plus participant demographics for the same 202 images.",{"name":84,"@type":75,"acceptedAnswer":85},"Which machine learning models are applied, and how are performance issues handled?",{"text":86,"@type":78},"The study applies Decision Trees, Logistic Regression, SVM, and XGBoost. It improves robustness by addressing class imbalances during modeling.","https://schema.org",{"og:url":53,"og:type":89,"og:title":13,"og:site_name":60,"og:description":14},"article",{"robots":91,"canonical":53},"index,follow",{"doc_id":7,"site_id":25},{"code":4,"msg":5,"data":94},[95,99,103,107,112,117,122,125,129,132,136],{"id":21,"doc_module":4,"doc_module_name":47,"category_name":96,"show_sort_weight":97,"slug":98},"Story & Novel",90,"story-novel",{"id":48,"doc_module":4,"doc_module_name":47,"category_name":100,"show_sort_weight":101,"slug":102},"Literature",80,"literature",{"id":54,"doc_module":4,"doc_module_name":47,"category_name":104,"show_sort_weight":105,"slug":106},"Exam",70,"exam",{"id":108,"doc_module":4,"doc_module_name":47,"category_name":109,"show_sort_weight":110,"slug":111},5,"Comic",60,"comic",{"id":113,"doc_module":4,"doc_module_name":47,"category_name":114,"show_sort_weight":115,"slug":116},6,"Technology",50,"technology",{"id":118,"doc_module":4,"doc_module_name":47,"category_name":119,"show_sort_weight":120,"slug":121},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":47,"category_name":12,"show_sort_weight":123,"slug":124},30,"research-report",{"id":20,"doc_module":4,"doc_module_name":47,"category_name":126,"show_sort_weight":127,"slug":128},"Religion & Spirituality",20,"religion-spirituality",{"id":127,"doc_module":4,"doc_module_name":47,"category_name":130,"show_sort_weight":127,"slug":131},"World Cup","world-cup",{"id":133,"doc_module":4,"doc_module_name":47,"category_name":134,"show_sort_weight":133,"slug":135},10,"Lifestyle","lifestyle",{"id":137,"doc_module":4,"doc_module_name":47,"category_name":138,"show_sort_weight":108,"slug":139},19,"General","general"]