Emotionally-relevant features for classification and regression of music lyrics
Autor(a) principal: | |
---|---|
Data de Publicação: | 2016 |
Outros Autores: | , , |
Tipo de documento: | Artigo |
Idioma: | eng |
Título da fonte: | Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) |
Texto Completo: | https://doi.org/10.1109/TAFFC.2016.2598569 |
Resumo: | This research addresses the role of lyrics in the music emotion recognition process. Our approach is based on several state of the art features complemented by novel stylistic, structural and semantic features. To evaluate our approach, we created a ground truth dataset containing 180 song lyrics, according to Russell?s emotion model. We conduct four types of experiments: regression and classification by quadrant, arousal and valence categories. Comparing to the state of the art features (ngrams - baseline), adding other features, including novel features, improved the F-measure from 69.9%, 82.7% and 85.6% to 80.1%, 88.3% and 90%, respectively for the three classification experiments. To study the relation between features and emotions (quadrants) we performed experiments to identify the best features that allow to describe and discriminate each quadrant. To further validate these experiments, we built a validation set comprising 771 lyrics extracted from the AllMusic platform, having achieved 73.6% F-measure in the classification by quadrants. We also conducted experiments to identify interpretable rules that show the relation between features and emotions and the relation among features. Regarding regression, results show that, comparing to similar studies for audio, we achieve a similar performance for arousal and a much better performance for valence. |
id |
RCAP_99ca2b36ee37cab04fb6cc62208a0ea4 |
---|---|
oai_identifier_str |
oai:repositorio.ismt.pt:123456789/720 |
network_acronym_str |
RCAP |
network_name_str |
Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) |
repository_id_str |
7160 |
spelling |
Emotionally-relevant features for classification and regression of music lyricsrecognition of group emotionaffective computingaffective computing applicationsmusic retrieval and generationnatural language processingThis research addresses the role of lyrics in the music emotion recognition process. Our approach is based on several state of the art features complemented by novel stylistic, structural and semantic features. To evaluate our approach, we created a ground truth dataset containing 180 song lyrics, according to Russell?s emotion model. We conduct four types of experiments: regression and classification by quadrant, arousal and valence categories. Comparing to the state of the art features (ngrams - baseline), adding other features, including novel features, improved the F-measure from 69.9%, 82.7% and 85.6% to 80.1%, 88.3% and 90%, respectively for the three classification experiments. To study the relation between features and emotions (quadrants) we performed experiments to identify the best features that allow to describe and discriminate each quadrant. To further validate these experiments, we built a validation set comprising 771 lyrics extracted from the AllMusic platform, having achieved 73.6% F-measure in the classification by quadrants. We also conducted experiments to identify interpretable rules that show the relation between features and emotions and the relation among features. Regarding regression, results show that, comparing to similar studies for audio, we achieve a similar performance for arousal and a much better performance for valence.IEEE TRANSACTIONS ON JOURNAL AFFECTIVE COMPUTING, MANUSCRIPT ID2017-10-13T14:43:10Z2017-10-132016-08-08T00:00:00Zinfo:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/articleapplication/pdfhttps://doi.org/10.1109/TAFFC.2016.2598569https://doi.org/10.1109/TAFFC.2016.2598569enghttp://repositorio.ismt.pt/handle/123456789/720Malheiro, RicardoPanda, RenatoGomes, PauloPaiva, Rui Pedroinfo: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:RCAAP2023-12-15T14:57:53Zoai:repositorio.ismt.pt:123456789/720Portal AgregadorONGhttps://www.rcaap.pt/oai/openaireopendoar:71602024-03-20T00:53:43.901491Repositório 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 |
Emotionally-relevant features for classification and regression of music lyrics |
title |
Emotionally-relevant features for classification and regression of music lyrics |
spellingShingle |
Emotionally-relevant features for classification and regression of music lyrics Malheiro, Ricardo recognition of group emotion affective computing affective computing applications music retrieval and generation natural language processing |
title_short |
Emotionally-relevant features for classification and regression of music lyrics |
title_full |
Emotionally-relevant features for classification and regression of music lyrics |
title_fullStr |
Emotionally-relevant features for classification and regression of music lyrics |
title_full_unstemmed |
Emotionally-relevant features for classification and regression of music lyrics |
title_sort |
Emotionally-relevant features for classification and regression of music lyrics |
author |
Malheiro, Ricardo |
author_facet |
Malheiro, Ricardo Panda, Renato Gomes, Paulo Paiva, Rui Pedro |
author_role |
author |
author2 |
Panda, Renato Gomes, Paulo Paiva, Rui Pedro |
author2_role |
author author author |
dc.contributor.author.fl_str_mv |
Malheiro, Ricardo Panda, Renato Gomes, Paulo Paiva, Rui Pedro |
dc.subject.por.fl_str_mv |
recognition of group emotion affective computing affective computing applications music retrieval and generation natural language processing |
topic |
recognition of group emotion affective computing affective computing applications music retrieval and generation natural language processing |
description |
This research addresses the role of lyrics in the music emotion recognition process. Our approach is based on several state of the art features complemented by novel stylistic, structural and semantic features. To evaluate our approach, we created a ground truth dataset containing 180 song lyrics, according to Russell?s emotion model. We conduct four types of experiments: regression and classification by quadrant, arousal and valence categories. Comparing to the state of the art features (ngrams - baseline), adding other features, including novel features, improved the F-measure from 69.9%, 82.7% and 85.6% to 80.1%, 88.3% and 90%, respectively for the three classification experiments. To study the relation between features and emotions (quadrants) we performed experiments to identify the best features that allow to describe and discriminate each quadrant. To further validate these experiments, we built a validation set comprising 771 lyrics extracted from the AllMusic platform, having achieved 73.6% F-measure in the classification by quadrants. We also conducted experiments to identify interpretable rules that show the relation between features and emotions and the relation among features. Regarding regression, results show that, comparing to similar studies for audio, we achieve a similar performance for arousal and a much better performance for valence. |
publishDate |
2016 |
dc.date.none.fl_str_mv |
2016-08-08T00:00:00Z 2017-10-13T14:43:10Z 2017-10-13 |
dc.type.status.fl_str_mv |
info:eu-repo/semantics/publishedVersion |
dc.type.driver.fl_str_mv |
info:eu-repo/semantics/article |
format |
article |
status_str |
publishedVersion |
dc.identifier.uri.fl_str_mv |
https://doi.org/10.1109/TAFFC.2016.2598569 https://doi.org/10.1109/TAFFC.2016.2598569 |
url |
https://doi.org/10.1109/TAFFC.2016.2598569 |
dc.language.iso.fl_str_mv |
eng |
language |
eng |
dc.relation.none.fl_str_mv |
http://repositorio.ismt.pt/handle/123456789/720 |
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.publisher.none.fl_str_mv |
IEEE TRANSACTIONS ON JOURNAL AFFECTIVE COMPUTING, MANUSCRIPT ID |
publisher.none.fl_str_mv |
IEEE TRANSACTIONS ON JOURNAL AFFECTIVE COMPUTING, MANUSCRIPT ID |
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_ |
1799136425384345600 |