Discrete to dimensional physiological emotion classification

Detalhes bibliográficos
Autor(a) principal: Alves, Carolina Fernandes
Data de Publicação: 2021
Tipo de documento: Dissertação
Idioma: eng
Título da fonte: Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)
Texto Completo: http://hdl.handle.net/10773/33692
Resumo: Emotions play a very important role in human life. The way we communicate and interact with others, our actions, thoughts, are all influenced by them, whether in a positive or negative way. Unfortunately, there is a variety of mental diseases, like anxiety and depression, that are characterized by a prevalence of negative emotions, and in which people tend to have a higher difficulty in understanding their emotional state. Consequently, the importance of each one of us being able to identify their emotional state is crucial to guarantee a healthy control over emotions. The emotion recognition systems can be one of the solutions to help people identify and interpret their emotions, hence increasing their well-being and health. Studies in this area have explored different topics ranging from the type of signals and features to the method of feature selection and emotional classification. Furthermore, they also began to diverge in the approach of describing emotions, which can be discrete or dimensional. In this work, the two approaches were studied to understand the impact of the emotional description on the classification process and to conclude on the most adequate approach to identify emotions. To this end, it was created a database of the physiological signals: electrocardiogram, electrodermal activity and electromyogram of the medial frontalis and trapezius muscles. An exploratory analysis was performed with these data revealing that the electrocardiogram and electrodermal activity represent the most informative in emotion discrimination. Nevertheless, in a multivariable approach, the features from electromyogram reveal to be useful on emotion classification. The approach initially studied was based on a discrete model of emotions, however, misclassification of some observations led to considering the hypothesis of testing a dimensional model (valence/arousal). This model proved to be more robust than the previous one, which led to the conclusion that it is better adapted to both emotional response and the individual response to the stimulus, confirming its best description of the emotion.
id RCAP_dc1eb203cbcddd721ddce8651e7451f8
oai_identifier_str oai:ria.ua.pt:10773/33692
network_acronym_str RCAP
network_name_str Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)
repository_id_str 7160
spelling Discrete to dimensional physiological emotion classificationEmotionEmotion elicitationPhysiological signalsClassificationDiscrete modelDimensional modelEmotions play a very important role in human life. The way we communicate and interact with others, our actions, thoughts, are all influenced by them, whether in a positive or negative way. Unfortunately, there is a variety of mental diseases, like anxiety and depression, that are characterized by a prevalence of negative emotions, and in which people tend to have a higher difficulty in understanding their emotional state. Consequently, the importance of each one of us being able to identify their emotional state is crucial to guarantee a healthy control over emotions. The emotion recognition systems can be one of the solutions to help people identify and interpret their emotions, hence increasing their well-being and health. Studies in this area have explored different topics ranging from the type of signals and features to the method of feature selection and emotional classification. Furthermore, they also began to diverge in the approach of describing emotions, which can be discrete or dimensional. In this work, the two approaches were studied to understand the impact of the emotional description on the classification process and to conclude on the most adequate approach to identify emotions. To this end, it was created a database of the physiological signals: electrocardiogram, electrodermal activity and electromyogram of the medial frontalis and trapezius muscles. An exploratory analysis was performed with these data revealing that the electrocardiogram and electrodermal activity represent the most informative in emotion discrimination. Nevertheless, in a multivariable approach, the features from electromyogram reveal to be useful on emotion classification. The approach initially studied was based on a discrete model of emotions, however, misclassification of some observations led to considering the hypothesis of testing a dimensional model (valence/arousal). This model proved to be more robust than the previous one, which led to the conclusion that it is better adapted to both emotional response and the individual response to the stimulus, confirming its best description of the emotion.As emoções desempenham um papel muito importante na vida humana. A maneira como nós comunicamos e interagimos uns com os outros, as nossas ações e pensamentos, são todos influenciados por elas, seja de uma forma positiva ou negativa. Infelizmente, existe uma variedade de doenças mentais, como a ansiedade e depressão, que são caracterizadas por uma prevalência de emoções negativas e nas quais as pessoas tendem a ter uma maior dificuldade em compreender o seu estado emocional. Consequentemente, é muito importante que cada um de nós seja capaz de identificar as nossas emoções, de forma a garantir que as conseguimos controlar e que o efeito contrário não ocorra. Os sistemas de reconhecimento de emoções podem ser uma das soluções para ajudar as pessoas a identificar as suas emoções, levando a uma melhoria do seu bem-estar e saúde. Os estudos nesta área têm explorado diferentes tópicos que vão desde o tipo de sinais e características, ao método de seleção de características e de classificação emocional. Além disso, também começaram a divergir na abordagem para descrever as emoções, que pode ser discreta (e.g. alegria, medo) ou dimensional (e.g. nível de agradabilidade, ativação). Neste trabalho, as duas abordagens foram estudadas de forma a compreender o impacto da descrição emocional no processo de classificação e, assim, concluir sobre a abordagem mais adequada para identificar as emoções. Para tal, foi criada uma base de dados constituída pelos sinais fisiológicos: eletrocardiograma, atividade eletrodérmica e eletromiograma dos músculos medial frontal e trapézio. A análise exploratória destes dados permitiu descrever as emoções do ponto de vista da resposta fisiológica. O eletrocardiograma e a atividade eletrodérmica apresentaram-se como sendo os sinais que melhor discriminam a atividade emocional (têm o maior número de características que distinguem os estados emocionais). Numa análise multivariável, verificou-se que a informação do eletromiograma também era uma fonte discriminatória, uma vez que as suas características eram sistematicamente selecionadas pelo classificador. A abordagem inicialmente estudada assentou sobre o modelo discreto de emoções, contudo a classificação errada de algumas observações levou a ponderar a hipótese de testar um modelo dimensional (agradabilidade/ativação). Este modelo revelou-se mais robusto que o anterior, o que levou a concluir que se adapta melhor quer à resposta da emoção, quer à resposta individual de cada pessoa ao estímulo. Comprovando assim a sua melhor descrição da emoção.2022-12-03T00:00:00Z2021-11-22T00:00:00Z2021-11-22info:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/masterThesisapplication/pdfhttp://hdl.handle.net/10773/33692engAlves, Carolina Fernandesinfo:eu-repo/semantics/embargoedAccessreponame:Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)instname:Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informaçãoinstacron:RCAAP2024-02-22T12:04:49Zoai:ria.ua.pt:10773/33692Portal AgregadorONGhttps://www.rcaap.pt/oai/openaireopendoar:71602024-03-20T03:05:03.468584Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) - Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informaçãofalse
dc.title.none.fl_str_mv Discrete to dimensional physiological emotion classification
title Discrete to dimensional physiological emotion classification
spellingShingle Discrete to dimensional physiological emotion classification
Alves, Carolina Fernandes
Emotion
Emotion elicitation
Physiological signals
Classification
Discrete model
Dimensional model
title_short Discrete to dimensional physiological emotion classification
title_full Discrete to dimensional physiological emotion classification
title_fullStr Discrete to dimensional physiological emotion classification
title_full_unstemmed Discrete to dimensional physiological emotion classification
title_sort Discrete to dimensional physiological emotion classification
author Alves, Carolina Fernandes
author_facet Alves, Carolina Fernandes
author_role author
dc.contributor.author.fl_str_mv Alves, Carolina Fernandes
dc.subject.por.fl_str_mv Emotion
Emotion elicitation
Physiological signals
Classification
Discrete model
Dimensional model
topic Emotion
Emotion elicitation
Physiological signals
Classification
Discrete model
Dimensional model
description Emotions play a very important role in human life. The way we communicate and interact with others, our actions, thoughts, are all influenced by them, whether in a positive or negative way. Unfortunately, there is a variety of mental diseases, like anxiety and depression, that are characterized by a prevalence of negative emotions, and in which people tend to have a higher difficulty in understanding their emotional state. Consequently, the importance of each one of us being able to identify their emotional state is crucial to guarantee a healthy control over emotions. The emotion recognition systems can be one of the solutions to help people identify and interpret their emotions, hence increasing their well-being and health. Studies in this area have explored different topics ranging from the type of signals and features to the method of feature selection and emotional classification. Furthermore, they also began to diverge in the approach of describing emotions, which can be discrete or dimensional. In this work, the two approaches were studied to understand the impact of the emotional description on the classification process and to conclude on the most adequate approach to identify emotions. To this end, it was created a database of the physiological signals: electrocardiogram, electrodermal activity and electromyogram of the medial frontalis and trapezius muscles. An exploratory analysis was performed with these data revealing that the electrocardiogram and electrodermal activity represent the most informative in emotion discrimination. Nevertheless, in a multivariable approach, the features from electromyogram reveal to be useful on emotion classification. The approach initially studied was based on a discrete model of emotions, however, misclassification of some observations led to considering the hypothesis of testing a dimensional model (valence/arousal). This model proved to be more robust than the previous one, which led to the conclusion that it is better adapted to both emotional response and the individual response to the stimulus, confirming its best description of the emotion.
publishDate 2021
dc.date.none.fl_str_mv 2021-11-22T00:00:00Z
2021-11-22
2022-12-03T00:00:00Z
dc.type.status.fl_str_mv info:eu-repo/semantics/publishedVersion
dc.type.driver.fl_str_mv info:eu-repo/semantics/masterThesis
format masterThesis
status_str publishedVersion
dc.identifier.uri.fl_str_mv http://hdl.handle.net/10773/33692
url http://hdl.handle.net/10773/33692
dc.language.iso.fl_str_mv eng
language eng
dc.rights.driver.fl_str_mv info:eu-repo/semantics/embargoedAccess
eu_rights_str_mv embargoedAccess
dc.format.none.fl_str_mv application/pdf
dc.source.none.fl_str_mv reponame:Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)
instname:Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informação
instacron:RCAAP
instname_str Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informação
instacron_str RCAAP
institution RCAAP
reponame_str Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)
collection Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)
repository.name.fl_str_mv Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) - Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informação
repository.mail.fl_str_mv
_version_ 1799137705697738752