Repository logo
 
Publication

How Does the Spotify API Compare to the Music Emotion Recognition State-of-the-Art?

2021-07-01Conference object Open access
Simple item page
dc.contributor.authorPanda, Renato
dc.contributor.authorRedinho, Hugo
dc.contributor.authorGonçalves, Carolina
dc.contributor.authorMalheiro, Ricardo
dc.contributor.authorPaiva, Rui Pedro
dc.date.accessioned2021-10-25T12:19:58Z
dc.date.available2021-10-25T12:19:58Z
dc.date.issued2021-07-01
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_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_PT
dc.description.versioninfo:eu-repo/semantics/publishedVersionpt_PT
dc.identifier.doi10.5281/zenodo.5045100pt_PT
dc.identifier.urihttp://hdl.handle.net/10400.26/37781
dc.language.isoengpt_PT
dc.peerreviewedyespt_PT
dc.publisherAxea sas/SMC Networkpt_PT
dc.relationSmart Cities Research Center
dc.rights.urihttp://creativecommons.org/licenses/by/4.0/pt_PT
dc.subjectSpotifypt_PT
dc.subjectaudio featurespt_PT
dc.subjectemotionpt_PT
dc.subjectmusicpt_PT
dc.subjectmusic emotion recognitionpt_PT
dc.titleHow Does the Spotify API Compare to the Music Emotion Recognition State-of-the-Art?pt_PT
dc.typeconference object
dspace.entity.typePublication
oaire.awardTitleSmart Cities Research Center
oaire.awardURIinfo:eu-repo/grantAgreement/FCT/6817 - DCRRNI ID/UIDP%2F05567%2F2020/PT
oaire.citation.endPage245pt_PT
oaire.citation.startPage238pt_PT
oaire.citation.title18th Sound and Music Computing Conference (SMC 2021)pt_PT
oaire.fundingStream6817 - DCRRNI ID
person.familyNamePanda
person.familyNameMalheiro
person.familyNamePinto de Carvalho e Paiva
person.givenNameRenato
person.givenNameRicardo
person.givenNameRui Pedro
person.identifierWT5afVUAAAAJ
person.identifier.ciencia-id661A-31CC-8D19
person.identifier.ciencia-idB81A-CB99-A4DF
person.identifier.ciencia-idAA16-002F-5AE3
person.identifier.orcid0000-0003-2539-5590
person.identifier.orcid0000-0002-3010-2732
person.identifier.orcid0000-0003-3215-3960
person.identifier.ridL-9369-2017
person.identifier.scopus-author-id55354413900
project.funder.identifierhttp://doi.org/10.13039/501100001871
project.funder.nameFundação para a Ciência e a Tecnologia
rcaap.rightsopenAccesspt_PT
rcaap.typeconferenceObjectpt_PT
relation.isAuthorOfPublication9cd470af-3968-45cc-ad6f-3b59e00ae823
relation.isAuthorOfPublicationd38dd344-0942-4fcb-b740-a4713fb170e7
relation.isAuthorOfPublication238ee6f8-61cd-49b4-9392-9e7763fd35f3
relation.isAuthorOfPublication.latestForDiscovery238ee6f8-61cd-49b4-9392-9e7763fd35f3
relation.isProjectOfPublication91a1f43f-7ed3-4791-8ded-837ad57c2f14
relation.isProjectOfPublication.latestForDiscovery91a1f43f-7ed3-4791-8ded-837ad57c2f14

Files

Original bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
Panda et al. - 2021 - How Does the Spotify API Compare to the Music Emotion Recognition State-of-the-Art.pdf
Size:
961.86 KB
Format:
Adobe Portable Document Format
Download

Collections

IPT - Ci2 - Artigos em Conferências