Improving music genre classification using collaborative tagging data

Research output: Chapter in book/report/conference proceedingConference contributionResearchpeer review

Authors

Research Organisations

External Research Organisations

  • Georgia Institute of Technology
View graph of relations

Details

Original languageEnglish
Title of host publicationProceedings of the 2nd ACM International Conference on Web Search and Data Mining, WSDM'09
PublisherAssociation for Computing Machinery (ACM)
Pages84-93
Number of pages10
ISBN (print)9781605583907
Publication statusPublished - 9 Feb 2009
Event2nd ACM International Conference on Web Search and Data Mining, WSDM'09 - Barcelona, Spain
Duration: 9 Feb 200912 Feb 2009

Publication series

NameProceedings of the 2nd ACM International Conference on Web Search and Data Mining, WSDM'09

Abstract

As a fundamental and critical component of music information retrieval (MIR) systems, music genre classification has attracted considerable research attention. Automatically classifying music by genre is, however, a challenging problem due to the fact that music is an evolving art. While most of the existing work categorizes music using features extracted from music audio signals, in this paper, we propose to exploit the semantic information embedded in tags supplied by users of social networking websites. Particularly, we consider the tag information by creating a graph of tracks so that tracks are neighbors if they are similar in terms of their associated tags. Two classification methods based on the track graph are developed. The first one employs a classification scheme which simultaneously considers the audio content and neighborhood of tracks. In contrast, the second one is a two-level classifier which initializes genre label for unknown tracks using their audio content, and then iteratively updates the genres considering the influence from their neighbors. A set of optimizing strategies are designed for the purpose of further enhancing the quality of the two-level classifier. Extensive experiments are conducted on real-world data collected from Last.fm. Promising experimental results demonstrate the benefit of using tags for accurate music genre classification.

Keywords

    Exploiting tag semantics, Music genre classification, Relaxation labelling

ASJC Scopus subject areas

Cite this

Improving music genre classification using collaborative tagging data. / Chen, Ling; Wright, Phillip; Nejdl, Wolfgang.
Proceedings of the 2nd ACM International Conference on Web Search and Data Mining, WSDM'09. Association for Computing Machinery (ACM), 2009. p. 84-93 (Proceedings of the 2nd ACM International Conference on Web Search and Data Mining, WSDM'09).

Research output: Chapter in book/report/conference proceedingConference contributionResearchpeer review

Chen, L, Wright, P & Nejdl, W 2009, Improving music genre classification using collaborative tagging data. in Proceedings of the 2nd ACM International Conference on Web Search and Data Mining, WSDM'09. Proceedings of the 2nd ACM International Conference on Web Search and Data Mining, WSDM'09, Association for Computing Machinery (ACM), pp. 84-93, 2nd ACM International Conference on Web Search and Data Mining, WSDM'09, Barcelona, Spain, 9 Feb 2009. https://doi.org/10.1145/1498759.1498812
Chen, L., Wright, P., & Nejdl, W. (2009). Improving music genre classification using collaborative tagging data. In Proceedings of the 2nd ACM International Conference on Web Search and Data Mining, WSDM'09 (pp. 84-93). (Proceedings of the 2nd ACM International Conference on Web Search and Data Mining, WSDM'09). Association for Computing Machinery (ACM). https://doi.org/10.1145/1498759.1498812
Chen L, Wright P, Nejdl W. Improving music genre classification using collaborative tagging data. In Proceedings of the 2nd ACM International Conference on Web Search and Data Mining, WSDM'09. Association for Computing Machinery (ACM). 2009. p. 84-93. (Proceedings of the 2nd ACM International Conference on Web Search and Data Mining, WSDM'09). doi: 10.1145/1498759.1498812
Chen, Ling ; Wright, Phillip ; Nejdl, Wolfgang. / Improving music genre classification using collaborative tagging data. Proceedings of the 2nd ACM International Conference on Web Search and Data Mining, WSDM'09. Association for Computing Machinery (ACM), 2009. pp. 84-93 (Proceedings of the 2nd ACM International Conference on Web Search and Data Mining, WSDM'09).
Download
@inproceedings{b65f23e673e34a6cb86c80238a3c3f8f,
title = "Improving music genre classification using collaborative tagging data",
abstract = "As a fundamental and critical component of music information retrieval (MIR) systems, music genre classification has attracted considerable research attention. Automatically classifying music by genre is, however, a challenging problem due to the fact that music is an evolving art. While most of the existing work categorizes music using features extracted from music audio signals, in this paper, we propose to exploit the semantic information embedded in tags supplied by users of social networking websites. Particularly, we consider the tag information by creating a graph of tracks so that tracks are neighbors if they are similar in terms of their associated tags. Two classification methods based on the track graph are developed. The first one employs a classification scheme which simultaneously considers the audio content and neighborhood of tracks. In contrast, the second one is a two-level classifier which initializes genre label for unknown tracks using their audio content, and then iteratively updates the genres considering the influence from their neighbors. A set of optimizing strategies are designed for the purpose of further enhancing the quality of the two-level classifier. Extensive experiments are conducted on real-world data collected from Last.fm. Promising experimental results demonstrate the benefit of using tags for accurate music genre classification.",
keywords = "Exploiting tag semantics, Music genre classification, Relaxation labelling",
author = "Ling Chen and Phillip Wright and Wolfgang Nejdl",
year = "2009",
month = feb,
day = "9",
doi = "10.1145/1498759.1498812",
language = "English",
isbn = "9781605583907",
series = "Proceedings of the 2nd ACM International Conference on Web Search and Data Mining, WSDM'09",
publisher = "Association for Computing Machinery (ACM)",
pages = "84--93",
booktitle = "Proceedings of the 2nd ACM International Conference on Web Search and Data Mining, WSDM'09",
address = "United States",
note = "2nd ACM International Conference on Web Search and Data Mining, WSDM'09 ; Conference date: 09-02-2009 Through 12-02-2009",

}

Download

TY - GEN

T1 - Improving music genre classification using collaborative tagging data

AU - Chen, Ling

AU - Wright, Phillip

AU - Nejdl, Wolfgang

PY - 2009/2/9

Y1 - 2009/2/9

N2 - As a fundamental and critical component of music information retrieval (MIR) systems, music genre classification has attracted considerable research attention. Automatically classifying music by genre is, however, a challenging problem due to the fact that music is an evolving art. While most of the existing work categorizes music using features extracted from music audio signals, in this paper, we propose to exploit the semantic information embedded in tags supplied by users of social networking websites. Particularly, we consider the tag information by creating a graph of tracks so that tracks are neighbors if they are similar in terms of their associated tags. Two classification methods based on the track graph are developed. The first one employs a classification scheme which simultaneously considers the audio content and neighborhood of tracks. In contrast, the second one is a two-level classifier which initializes genre label for unknown tracks using their audio content, and then iteratively updates the genres considering the influence from their neighbors. A set of optimizing strategies are designed for the purpose of further enhancing the quality of the two-level classifier. Extensive experiments are conducted on real-world data collected from Last.fm. Promising experimental results demonstrate the benefit of using tags for accurate music genre classification.

AB - As a fundamental and critical component of music information retrieval (MIR) systems, music genre classification has attracted considerable research attention. Automatically classifying music by genre is, however, a challenging problem due to the fact that music is an evolving art. While most of the existing work categorizes music using features extracted from music audio signals, in this paper, we propose to exploit the semantic information embedded in tags supplied by users of social networking websites. Particularly, we consider the tag information by creating a graph of tracks so that tracks are neighbors if they are similar in terms of their associated tags. Two classification methods based on the track graph are developed. The first one employs a classification scheme which simultaneously considers the audio content and neighborhood of tracks. In contrast, the second one is a two-level classifier which initializes genre label for unknown tracks using their audio content, and then iteratively updates the genres considering the influence from their neighbors. A set of optimizing strategies are designed for the purpose of further enhancing the quality of the two-level classifier. Extensive experiments are conducted on real-world data collected from Last.fm. Promising experimental results demonstrate the benefit of using tags for accurate music genre classification.

KW - Exploiting tag semantics

KW - Music genre classification

KW - Relaxation labelling

UR - http://www.scopus.com/inward/record.url?scp=70349129938&partnerID=8YFLogxK

U2 - 10.1145/1498759.1498812

DO - 10.1145/1498759.1498812

M3 - Conference contribution

AN - SCOPUS:70349129938

SN - 9781605583907

T3 - Proceedings of the 2nd ACM International Conference on Web Search and Data Mining, WSDM'09

SP - 84

EP - 93

BT - Proceedings of the 2nd ACM International Conference on Web Search and Data Mining, WSDM'09

PB - Association for Computing Machinery (ACM)

T2 - 2nd ACM International Conference on Web Search and Data Mining, WSDM'09

Y2 - 9 February 2009 through 12 February 2009

ER -

By the same author(s)