[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-127430-en":3,"doc-seo-127430-105":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},127430,962085564807,"Aurelia","https://ap-avatar.wpscdn.com/davatar_6f874abed73319feea01a86fa6f0fab8",8,"Research & Report","Machine Learning Methods in Music Emotion Recognition - Master’s Dissertation","Music Emotion Recognition (MER), a field within Music Information Retrieval (MIR), focuses on identifying emotions evoked in listeners by music. The dissertation formulates MER as a regression problem and evaluates machine learning approaches aimed at improving predictive accuracy and interpretability. Special attention is given to interpretable modeling through Shapley Values and dynamic linear models, supporting analysis of how features contribute to emotion predictions. The work also outlines data and modeling choices, and discusses results in the context of MER methodology.","Machine Learning Methods in Music Emotion Recognition  \nKarolayne Pereira Dessabato Supervisor: Hugo Tremonte de Carvalho  \nFederal University of Rio de Janeiro Institute of Mathematics Department of Statistical Methods 2025  \nMachine Learning Methods in Music Emotion Recognition  \nKarolayne Pereira Dessabato  \nDisserta¸c˜ao de Mestrado submetida ao Programa de P´os-Gradua¸c˜ao em Estat´ıstica do Instituto de Matem´atica da Universidade Federal do Rio de Janeiro-UFRJ, como parte dos requisitos necess´arios `a obten¸c˜ao do t´ıtulo de Mestre em Estat´ıstica.  \nAprovada por:  \nHugo Tremonte de Carvalho D.Sc-IM-UFRJ (Supervisor)  \nCarlos Tadeu Pagani Zanini  \nPh.D. -IM-UFRJ  \nLuiz Wagner Pereira Biscainho  \nD.Sc. -DEL/Poli & PEE/COPPE-UFRJ  \nRio de Janeiro, RJ-Brasil  \n2025  \nCIP-Catalogação na Publicação  \nDessabato, Karolayne Pereira  \nD475m Machine Learning Methods in Music Emotion  \nRecognition / Karolayne Pereira Dessabato . --Rio de Janeiro, 2025.  \n89 f .  \nOrientador: Hugo Tremonte de Carvalho .  \nDissertação (mestrado) -Universidade Federal do Rio de Janeiro, Instituto de Matemática, Programade Pós-Graduação em Estatística, 2025.  \n1. Music Emotion Recognition . 2. Interpretable Machine Learning . 3. Shapley Values . 4. Dynamic Linear Models . 5. Music Information Retrieval . I . Carvalho, Hugo Tremonte de, orient. II . Título .  \nElaborado pelo Sistema de Geração Automática da UFRJ com os dados fornecidospelo(a) autor(a), sob a responsabilidade de Miguel Romeu Amorim Neto-CRB-7/6283 .  \n“ The flower that blooms in adversity is the most rare and beautiful of all.”  \nMulan.  \nAcknowledgement  \nAlthough the content of this work is written entirely in English, I have chosen to express the following words in Portuguese, my native language. The intention behind this is to ensure that those acknowledged understand their significant contribution to the completion of this dissertation.  \nPrimeiramente, gostaria de agradecer `a pessoa mais importante para a realiza¸c˜ao desta disserta¸c˜ao: a mim mesma. Especialmente por ter conseguido superar diversos desafios da vida acadˆemica. Ser a primeira a ter uma gradua¸c˜ao e, em breve, mestrado, potencialmente abrir´a portas mais tranquilas para as futuras gera¸c˜oes da minha fam´ılia e familiares.  \nAgrade¸co `a minha fam´ılia pelo apoio durante a escrita deste trabalho, bem como pelos incentivos para iniciar o doutorado (cenas para os pr´oximos cap´ıtulos) . E n˜ao posso deixar de mencionar o Ra´ı, meu pinscher favorito.  \nAgrade¸co tamb´em ao meu melhor amigo; meu grande amor, que conheci pouco antes do in´ıcio do mestrado. Al´em de ter sido meu grande suporte em todos os momentos dap´os-gradua¸c˜ao e da escrita desta disserta¸c˜ao, ele tamb´em me ajudou nas monitorias de Processos Estoc´asticos (ressalto que s´o fui essa boa monitora por sua causa!) . Obrigadamais uma vez, te amo muito Rafael Souza dos Santos, ainda temos muitos restaurantes com estrela Michelin para conhecer ♡ .  \nAgrade¸co tamb´em ao MESTRE SUPREMO HUGO TREMONTE DE CARVALHO. Ele n˜ao ´e somente um orientador sensacional e um amigo encorajador, mas tamb´em ´e um baita cr´ıtico gastronˆomico, que me apresentou `a mais alta culin´aria, como o hamb´urguerde doce de leite (Malz), hot filadog (GORU) e o bolo russo de mel (Medovik) . Obrigadapor ter me aturado tanto LEK, mesmo vocˆe julgando meu hot com ketchup.  \nAgrade¸co imensamente `a banca pela disponibilidade de avaliar essa pesquisa, feita com tanto carinho e uma pitada de estresse. Carlos Tadeu e Luiz Wagner s˜ao docentes incr´ıveis com quem tive a honra de ter tido aula durante o per´ıodo do mestrado. Al´em  \nde brilhantes, vocˆes dois s˜ao pessoas maravilhosas fora da sala de aula. Tenho muitorespeito, admira¸c˜ao e carinho por vocˆes.  \nAgrade¸co ao Programa de P´os-Gradua¸c˜ao em Estat´ıstica (PPGE) pela oportunidade de realizar o mestrado em estat´ıstica, assim como `a Comiss˜ao Deliberativa da P´osGradua¸c˜ao do Programa em Estat´ıstica (CDPG) pelas reuni˜","cbCaigKVYNVX93Ba","https://ap.wps.com/l/cbCaigKVYNVX93Ba","pdf",1129438,1,102,"English","en",105,"# Acknowledgement\n## Purpose and contributors\n# Abstract\n## Problem framing and objectives\n# Keywords\n## Music Emotion Recognition (MER)","[{\"question\":\"What is the focus of this dissertation?\",\"answer\":\"It studies Music Emotion Recognition, aiming to predict the emotions evoked by music.\"},{\"question\":\"How is MER formulated in the work?\",\"answer\":\"MER is addressed as a regression task with the goal of learning emotion-related targets from music data.\"},{\"question\":\"Which interpretability methods are highlighted?\",\"answer\":\"The dissertation emphasizes interpretable machine learning using Shapley Values and dynamic linear models to explain model behavior and feature contributions.\"}]","Machine Learning Methods in Music Emotion Recognition - Master’s Dissertation | PDF",1785938831,257,{"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},"machine-learning-methods-in-music-emotion-recognition-masters-dissertation","",{"@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/machine-learning-methods-in-music-emotion-recognition-masters-dissertation/127430/",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],{"name":72,"@type":73,"acceptedAnswer":74},"What is the focus of this dissertation?","Question",{"text":75,"@type":76},"It studies Music Emotion Recognition, aiming to predict the emotions evoked by music.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How is MER formulated in the work?",{"text":80,"@type":76},"MER is addressed as a regression task with the goal of learning emotion-related targets from music data.",{"name":82,"@type":73,"acceptedAnswer":83},"Which interpretability methods are highlighted?",{"text":84,"@type":76},"The dissertation emphasizes interpretable machine learning using Shapley Values and dynamic linear models to explain model behavior and feature contributions.","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"]