Toward a Fair Evaluation and Analysis of Feature Selection for Music Tag Classification

Accurate music tag classification of music clips has been attracting great attention recently, because it allows one to provide various music excerpts, including unpopular ones, to users based on the clips’ acoustic similarities. Given a user’s preferred music, acoustic feature...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Jonghoon Chae, Sung-Hyun Cho, Jaegyun Park, Dae-Won Kim, Jaesung Lee
Formato:	article
Lenguaje:	EN
Publicado:	IEEE 2021
Materias:	Music tag classification feature selection machine learning evolutionary algorithm Electrical engineering. Electronics. Nuclear engineering TK1-9971
Acceso en línea:	https://doaj.org/article/eea0b5a59a754dd8a54c04b6157527f7
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:eea0b5a59a754dd8a54c04b6157527f7
record_format	dspace
spelling	oai:doaj.org-article:eea0b5a59a754dd8a54c04b6157527f72021-11-18T00:07:44ZToward a Fair Evaluation and Analysis of Feature Selection for Music Tag Classification2169-353610.1109/ACCESS.2021.3123966https://doaj.org/article/eea0b5a59a754dd8a54c04b6157527f72021-01-01T00:00:00Zhttps://ieeexplore.ieee.org/document/9592766/https://doaj.org/toc/2169-3536Accurate music tag classification of music clips has been attracting great attention recently, because it allows one to provide various music excerpts, including unpopular ones, to users based on the clips’ acoustic similarities. Given a user’s preferred music, acoustic features are extracted and then fed into the classifier, which outputs the related tag to recommend new music. Furthermore, the accuracy of the tag classifiers can be improved by selecting the best feature subset based on the domain to which the tag belongs. However, recent studies have struggled to evaluate the superiority of various classifiers because they utilize different feature extractors. In this study, to conduct a direct comparison of existing methods of classification, we create 20 music datasets with the same acoustic feature structure. In addition, we propose an effective evolutionary feature selection algorithm to evaluate the effectiveness of feature selection for tag classification. Our experiments demonstrate that the proposed method improves the accuracy of tag classification, and the analysis with multiple datasets provides valuable insights, such as the important features for general music tag classification in target domains.Jonghoon ChaeSung-Hyun ChoJaegyun ParkDae-Won KimJaesung LeeIEEEarticleMusic tag classificationfeature selectionmachine learningevolutionary algorithmElectrical engineering. Electronics. Nuclear engineeringTK1-9971ENIEEE Access, Vol 9, Pp 147717-147731 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Music tag classification feature selection machine learning evolutionary algorithm Electrical engineering. Electronics. Nuclear engineering TK1-9971
spellingShingle	Music tag classification feature selection machine learning evolutionary algorithm Electrical engineering. Electronics. Nuclear engineering TK1-9971 Jonghoon Chae Sung-Hyun Cho Jaegyun Park Dae-Won Kim Jaesung Lee Toward a Fair Evaluation and Analysis of Feature Selection for Music Tag Classification
description	Accurate music tag classification of music clips has been attracting great attention recently, because it allows one to provide various music excerpts, including unpopular ones, to users based on the clips’ acoustic similarities. Given a user’s preferred music, acoustic features are extracted and then fed into the classifier, which outputs the related tag to recommend new music. Furthermore, the accuracy of the tag classifiers can be improved by selecting the best feature subset based on the domain to which the tag belongs. However, recent studies have struggled to evaluate the superiority of various classifiers because they utilize different feature extractors. In this study, to conduct a direct comparison of existing methods of classification, we create 20 music datasets with the same acoustic feature structure. In addition, we propose an effective evolutionary feature selection algorithm to evaluate the effectiveness of feature selection for tag classification. Our experiments demonstrate that the proposed method improves the accuracy of tag classification, and the analysis with multiple datasets provides valuable insights, such as the important features for general music tag classification in target domains.
format	article
author	Jonghoon Chae Sung-Hyun Cho Jaegyun Park Dae-Won Kim Jaesung Lee
author_facet	Jonghoon Chae Sung-Hyun Cho Jaegyun Park Dae-Won Kim Jaesung Lee
author_sort	Jonghoon Chae
title	Toward a Fair Evaluation and Analysis of Feature Selection for Music Tag Classification
title_short	Toward a Fair Evaluation and Analysis of Feature Selection for Music Tag Classification
title_full	Toward a Fair Evaluation and Analysis of Feature Selection for Music Tag Classification
title_fullStr	Toward a Fair Evaluation and Analysis of Feature Selection for Music Tag Classification
title_full_unstemmed	Toward a Fair Evaluation and Analysis of Feature Selection for Music Tag Classification
title_sort	toward a fair evaluation and analysis of feature selection for music tag classification
publisher	IEEE
publishDate	2021
url	https://doaj.org/article/eea0b5a59a754dd8a54c04b6157527f7
work_keys_str_mv	AT jonghoonchae towardafairevaluationandanalysisoffeatureselectionformusictagclassification AT sunghyuncho towardafairevaluationandanalysisoffeatureselectionformusictagclassification AT jaegyunpark towardafairevaluationandanalysisoffeatureselectionformusictagclassification AT daewonkim towardafairevaluationandanalysisoffeatureselectionformusictagclassification AT jaesunglee towardafairevaluationandanalysisoffeatureselectionformusictagclassification
_version_	1718425258808049664

Toward a Fair Evaluation and Analysis of Feature Selection for Music Tag Classification

Ejemplares similares