Please use this identifier to cite or link to this item: http://hdl.handle.net/10316/95161
DC FieldValueLanguage
dc.contributor.authorPanda, Renato-
dc.contributor.authorRedinho, Hugo-
dc.contributor.authorGonçalves, Carolina-
dc.contributor.authorMalheiro, Ricardo-
dc.contributor.authorPaiva, Rui Pedro-
dc.date.accessioned2021-07-04T16:31:54Z-
dc.date.available2021-07-04T16:31:54Z-
dc.date.issued2021-07-01-
dc.identifier.urihttp://hdl.handle.net/10316/95161-
dc.description.abstractFeatures are arguably the key factor to any machine learning problem. Over the decades, myriads of audio features and recently feature-learning approaches have been tested in Music Emotion Recognition (MER) with scarce improvements. Here, we shed some light on the suitability of the audio features provided by the Spotify API, the leading music streaming service, when applied to MER. To this end, 12 Spotify API features were obtained for 704 of our 900-song dataset, annotated in terms of Russell’s quadrants. These are compared to emotionally-relevant features obtained previously, using feature ranking and emotion classification experiments. We verified that energy, valence and acousticness features from Spotify are highly relevant to MER. However, the 12-feature set is unable to meet the performance of the features available in the state-of-the-art (58.5% vs. 74.7% F1-measure). Combining Spotify and state-of-the-art sets leads to small improvements with fewer features (top5: +2.3%, top10: +1.1%), while not improving the maximum results (100 features). From this we conclude that Spotify provides some higher-level emotionally-relevant features. Such extractors are desirable, since they are closer to human concepts and allow for interpretable rules to be extracted (harder with hundreds of abstract features). Still, additional emotionally-relevant features are needed to improve MER.pt
dc.description.sponsorshipThis work was supported by CISUC (Center for Informatics and Systems of the University of Coimbra). Renato Panda was supported by Ci2 - FCT UIDP/05567/2020.pt
dc.language.isoengpt
dc.publisherAxea sas/SMC Networkpt
dc.rightsopenAccesspt
dc.rights.urihttp://creativecommons.org/licenses/by/4.0/pt
dc.subjectmusic emotion recognitionpt
dc.subjectSpotifypt
dc.subjectaudio featurespt
dc.subjectemotionpt
dc.subjectmusicpt
dc.titleHow Does the Spotify API Compare to the Music Emotion Recognition State-of-the-Art?pt
dc.typeconferenceObjectpt
degois.publication.firstPage238pt
degois.publication.lastPage245pt
degois.publication.titleProceedings of the 18th Sound and Music Computing Conference (SMC 2021)pt
dc.peerreviewedyespt
dc.identifier.doi10.5281/zenodo.5045100-
dc.date.embargo2021-07-01*
uc.date.periodoEmbargo0pt
item.fulltextCom Texto completo-
item.grantfulltextopen-
item.languageiso639-1en-
crisitem.author.deptFaculty of Sciences and Technology-
crisitem.author.deptFaculty of Sciences and Technology-
crisitem.author.deptFaculty of Sciences and Technology-
crisitem.author.parentdeptUniversity of Coimbra-
crisitem.author.parentdeptUniversity of Coimbra-
crisitem.author.parentdeptUniversity of Coimbra-
crisitem.author.researchunitCISUC - Centre for Informatics and Systems of the University of Coimbra-
crisitem.author.researchunitCISUC - Centre for Informatics and Systems of the University of Coimbra-
crisitem.author.researchunitCISUC - Centre for Informatics and Systems of the University of Coimbra-
crisitem.author.parentresearchunitFaculty of Sciences and Technology-
crisitem.author.parentresearchunitFaculty of Sciences and Technology-
crisitem.author.parentresearchunitFaculty of Sciences and Technology-
crisitem.author.orcid0000-0003-2539-5590-
crisitem.author.orcid0000-0002-3010-2732-
crisitem.author.orcid0000-0003-3215-3960-
Appears in Collections:I&D CISUC - Artigos em Livros de Actas
Show simple item record

Page view(s)

76
checked on Sep 17, 2021

Download(s)

45
checked on Sep 17, 2021

Google ScholarTM

Check

Altmetric

Altmetric


This item is licensed under a Creative Commons License Creative Commons