Sentiment analysis and topic modeling of Portuguese and Brazilian song lyrics through the years
Autor(a) principal: | |
---|---|
Data de Publicação: | 2023 |
Tipo de documento: | Dissertação |
Idioma: | eng |
Título da fonte: | Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) |
Texto Completo: | http://hdl.handle.net/10071/30770 |
Resumo: | Music lyrics are a rich source of information, within the various components in the musical context. With their distinctive identity and narrative elements, lyrics have the power to convey profound messages, with the emotions and sentiments they portray and the themes addressed. Over time, these lyrical components have evolved, mirroring the changing dynamics of society. This dissertation aims to study these sentiment and topic changes in the national scope of Portugal and Brazil, spanning from the 1960s to the 2020s. To achieve this, we employ a lexicon-based approach for sentiment analysis and utilize BERTopic and LDA for topic modeling. The results of our research reveal an emotional contrast between the two countries. Brazilian songs predominantly exude positivity and uplifting sentiments, while Portuguese songs often carry a prevailing undertone of negativity. The extracted topics from the lyrics frequently align with each nation’s historical and societal experiences. However, some instances show a disconnect, where lyrics do not accurately mirror challenging periods in terms of topics or sentiment polarities. This suggests that lyricists may employ their musical creations as a form of escape from reality. |
id |
RCAP_73d425b302ea088f4129e7f8269b8b1d |
---|---|
oai_identifier_str |
oai:repositorio.iscte-iul.pt:10071/30770 |
network_acronym_str |
RCAP |
network_name_str |
Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) |
repository_id_str |
7160 |
spelling |
Sentiment analysis and topic modeling of Portuguese and Brazilian song lyrics through the yearsMusic lyricsAnálise de sentimentos -- Sentiment analysisTopic modelText miningLetras de músicaModelação de tópicosMusic lyrics are a rich source of information, within the various components in the musical context. With their distinctive identity and narrative elements, lyrics have the power to convey profound messages, with the emotions and sentiments they portray and the themes addressed. Over time, these lyrical components have evolved, mirroring the changing dynamics of society. This dissertation aims to study these sentiment and topic changes in the national scope of Portugal and Brazil, spanning from the 1960s to the 2020s. To achieve this, we employ a lexicon-based approach for sentiment analysis and utilize BERTopic and LDA for topic modeling. The results of our research reveal an emotional contrast between the two countries. Brazilian songs predominantly exude positivity and uplifting sentiments, while Portuguese songs often carry a prevailing undertone of negativity. The extracted topics from the lyrics frequently align with each nation’s historical and societal experiences. However, some instances show a disconnect, where lyrics do not accurately mirror challenging periods in terms of topics or sentiment polarities. This suggests that lyricists may employ their musical creations as a form of escape from reality.As letras de uma música são uma rica fonte de informação, entre os diversos componentes no contexto musical. Com a sua identidade distinta e elementos narrativos, as letras têm o poder de transmitir mensagens profundas, com as emoções e os sentimentos retratados e os temas abordados. Ao longo do tempo, esses componentes líricos evoluíram, refletindo as mudanças nas dinâmicas da sociedade. Esta dissertação tem como objetivo estudar essas mudanças de sentimentos e tópicos no cenário nacional de Portugal e Brasil, abrangindo desde a década de 1960 até a década de 2020. Para alcançar estes objetivos, utilizamos uma abordagem baseada em léxico para análise de sentimentos e empregamos BERTopic e LDA para o modelo de tópicos. Os resultados das nossas pesquisas revelam um contraste emocional entre os dois países. As canções brasileiras predominantemente exalam positividade e sentimentos motivadores, enquanto que as canções portuguesas frequentemente carregam um tom de negatividade. Os tópicos extraídos das letras frequentemente se alinham com as experiências históricas e sociais de cada nação. No entanto, algumas instâncias mostram uma desconexão, onde as letras não refletem com precisão os períodos desafiadores, em termos de tópicos ou polaridades de sentimento. Isso sugere que os letristas podem usar as suas criações musicais como uma forma de escapar à realidade.2024-02-01T12:56:45Z2023-12-28T00:00:00Z2023-12-282023-10info:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/masterThesisapplication/pdfhttp://hdl.handle.net/10071/30770TID:203469569engD´Alva, Inês Mariana da Trindadeinfo:eu-repo/semantics/openAccessreponame:Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)instname:Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informaçãoinstacron:RCAAP2024-02-04T01:21:41Zoai:repositorio.iscte-iul.pt:10071/30770Portal AgregadorONGhttps://www.rcaap.pt/oai/openaireopendoar:71602024-03-20T02:08:08.417148Repositório 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 |
Sentiment analysis and topic modeling of Portuguese and Brazilian song lyrics through the years |
title |
Sentiment analysis and topic modeling of Portuguese and Brazilian song lyrics through the years |
spellingShingle |
Sentiment analysis and topic modeling of Portuguese and Brazilian song lyrics through the years D´Alva, Inês Mariana da Trindade Music lyrics Análise de sentimentos -- Sentiment analysis Topic model Text mining Letras de música Modelação de tópicos |
title_short |
Sentiment analysis and topic modeling of Portuguese and Brazilian song lyrics through the years |
title_full |
Sentiment analysis and topic modeling of Portuguese and Brazilian song lyrics through the years |
title_fullStr |
Sentiment analysis and topic modeling of Portuguese and Brazilian song lyrics through the years |
title_full_unstemmed |
Sentiment analysis and topic modeling of Portuguese and Brazilian song lyrics through the years |
title_sort |
Sentiment analysis and topic modeling of Portuguese and Brazilian song lyrics through the years |
author |
D´Alva, Inês Mariana da Trindade |
author_facet |
D´Alva, Inês Mariana da Trindade |
author_role |
author |
dc.contributor.author.fl_str_mv |
D´Alva, Inês Mariana da Trindade |
dc.subject.por.fl_str_mv |
Music lyrics Análise de sentimentos -- Sentiment analysis Topic model Text mining Letras de música Modelação de tópicos |
topic |
Music lyrics Análise de sentimentos -- Sentiment analysis Topic model Text mining Letras de música Modelação de tópicos |
description |
Music lyrics are a rich source of information, within the various components in the musical context. With their distinctive identity and narrative elements, lyrics have the power to convey profound messages, with the emotions and sentiments they portray and the themes addressed. Over time, these lyrical components have evolved, mirroring the changing dynamics of society. This dissertation aims to study these sentiment and topic changes in the national scope of Portugal and Brazil, spanning from the 1960s to the 2020s. To achieve this, we employ a lexicon-based approach for sentiment analysis and utilize BERTopic and LDA for topic modeling. The results of our research reveal an emotional contrast between the two countries. Brazilian songs predominantly exude positivity and uplifting sentiments, while Portuguese songs often carry a prevailing undertone of negativity. The extracted topics from the lyrics frequently align with each nation’s historical and societal experiences. However, some instances show a disconnect, where lyrics do not accurately mirror challenging periods in terms of topics or sentiment polarities. This suggests that lyricists may employ their musical creations as a form of escape from reality. |
publishDate |
2023 |
dc.date.none.fl_str_mv |
2023-12-28T00:00:00Z 2023-12-28 2023-10 2024-02-01T12:56:45Z |
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/10071/30770 TID:203469569 |
url |
http://hdl.handle.net/10071/30770 |
identifier_str_mv |
TID:203469569 |
dc.language.iso.fl_str_mv |
eng |
language |
eng |
dc.rights.driver.fl_str_mv |
info:eu-repo/semantics/openAccess |
eu_rights_str_mv |
openAccess |
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_ |
1799137170224578561 |