Quantify music artist similarity based on style and mood

Bo Shao, Tao Li, Mitsunori Ogihara

Research output: Chapter in Book/Report/Conference proceedingConference contribution

6 Citations (Scopus)

Abstract

Music artist similarity has been an active research topic in music information retrieval for a long time since it is especially useful for music recommendation and organization. However, it is a difficult problem. The similarity varies significantly due to different artistic aspects considered and most importantly, it is hard to quantify. In this paper, we propose a new framework for quantifying artist similarity. In the framework, we focus on style and mood aspects of artists whose descriptions are extracted from the authoritative information available at the All Music Guide website. We then generate style - mood joint taxonomies using hierarchical co-clustering algorithm, and quantify the semantic similarities between the style/mood terms based on the taxonomy structure and the positions of these terms in the taxonomies. Finally we calculate the artist similarities according to all the style/mood terms used to describe them. Experiments are conducted to show the effectiveness of our framework.

Original languageEnglish (US)
Title of host publicationInternational Conference on Information and Knowledge Management, Proceedings
Pages119-124
Number of pages6
DOIs
StatePublished - 2008
Event10th ACM Workshop on Web Information and Data Management, WIDM '08, Co-located with the ACM 17th Conference on Information and Knowledge Management, CIKM '08 - Napa Valley, CA, United States
Duration: Oct 26 2008Oct 30 2008

Other

Other10th ACM Workshop on Web Information and Data Management, WIDM '08, Co-located with the ACM 17th Conference on Information and Knowledge Management, CIKM '08
CountryUnited States
CityNapa Valley, CA
Period10/26/0810/30/08

Fingerprint

Mood
Music
Artist
Taxonomy
Semantic similarity
Web sites
Information retrieval
Clustering algorithm
Experiment

Keywords

  • Hierarchical co-clustering
  • Music artist similarity
  • Similarity quantification

ASJC Scopus subject areas

  • Business, Management and Accounting(all)
  • Decision Sciences(all)

Cite this

Shao, B., Li, T., & Ogihara, M. (2008). Quantify music artist similarity based on style and mood. In International Conference on Information and Knowledge Management, Proceedings (pp. 119-124) https://doi.org/10.1145/1458502.1458522

Quantify music artist similarity based on style and mood. / Shao, Bo; Li, Tao; Ogihara, Mitsunori.

International Conference on Information and Knowledge Management, Proceedings. 2008. p. 119-124.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Shao, B, Li, T & Ogihara, M 2008, Quantify music artist similarity based on style and mood. in International Conference on Information and Knowledge Management, Proceedings. pp. 119-124, 10th ACM Workshop on Web Information and Data Management, WIDM '08, Co-located with the ACM 17th Conference on Information and Knowledge Management, CIKM '08, Napa Valley, CA, United States, 10/26/08. https://doi.org/10.1145/1458502.1458522
Shao B, Li T, Ogihara M. Quantify music artist similarity based on style and mood. In International Conference on Information and Knowledge Management, Proceedings. 2008. p. 119-124 https://doi.org/10.1145/1458502.1458522
Shao, Bo ; Li, Tao ; Ogihara, Mitsunori. / Quantify music artist similarity based on style and mood. International Conference on Information and Knowledge Management, Proceedings. 2008. pp. 119-124
@inproceedings{491982ddc9aa42b2861abbc926f37f77,
title = "Quantify music artist similarity based on style and mood",
abstract = "Music artist similarity has been an active research topic in music information retrieval for a long time since it is especially useful for music recommendation and organization. However, it is a difficult problem. The similarity varies significantly due to different artistic aspects considered and most importantly, it is hard to quantify. In this paper, we propose a new framework for quantifying artist similarity. In the framework, we focus on style and mood aspects of artists whose descriptions are extracted from the authoritative information available at the All Music Guide website. We then generate style - mood joint taxonomies using hierarchical co-clustering algorithm, and quantify the semantic similarities between the style/mood terms based on the taxonomy structure and the positions of these terms in the taxonomies. Finally we calculate the artist similarities according to all the style/mood terms used to describe them. Experiments are conducted to show the effectiveness of our framework.",
keywords = "Hierarchical co-clustering, Music artist similarity, Similarity quantification",
author = "Bo Shao and Tao Li and Mitsunori Ogihara",
year = "2008",
doi = "10.1145/1458502.1458522",
language = "English (US)",
isbn = "9781605582603",
pages = "119--124",
booktitle = "International Conference on Information and Knowledge Management, Proceedings",

}

TY - GEN

T1 - Quantify music artist similarity based on style and mood

AU - Shao, Bo

AU - Li, Tao

AU - Ogihara, Mitsunori

PY - 2008

Y1 - 2008

N2 - Music artist similarity has been an active research topic in music information retrieval for a long time since it is especially useful for music recommendation and organization. However, it is a difficult problem. The similarity varies significantly due to different artistic aspects considered and most importantly, it is hard to quantify. In this paper, we propose a new framework for quantifying artist similarity. In the framework, we focus on style and mood aspects of artists whose descriptions are extracted from the authoritative information available at the All Music Guide website. We then generate style - mood joint taxonomies using hierarchical co-clustering algorithm, and quantify the semantic similarities between the style/mood terms based on the taxonomy structure and the positions of these terms in the taxonomies. Finally we calculate the artist similarities according to all the style/mood terms used to describe them. Experiments are conducted to show the effectiveness of our framework.

AB - Music artist similarity has been an active research topic in music information retrieval for a long time since it is especially useful for music recommendation and organization. However, it is a difficult problem. The similarity varies significantly due to different artistic aspects considered and most importantly, it is hard to quantify. In this paper, we propose a new framework for quantifying artist similarity. In the framework, we focus on style and mood aspects of artists whose descriptions are extracted from the authoritative information available at the All Music Guide website. We then generate style - mood joint taxonomies using hierarchical co-clustering algorithm, and quantify the semantic similarities between the style/mood terms based on the taxonomy structure and the positions of these terms in the taxonomies. Finally we calculate the artist similarities according to all the style/mood terms used to describe them. Experiments are conducted to show the effectiveness of our framework.

KW - Hierarchical co-clustering

KW - Music artist similarity

KW - Similarity quantification

UR - http://www.scopus.com/inward/record.url?scp=77951116816&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=77951116816&partnerID=8YFLogxK

U2 - 10.1145/1458502.1458522

DO - 10.1145/1458502.1458522

M3 - Conference contribution

SN - 9781605582603

SP - 119

EP - 124

BT - International Conference on Information and Knowledge Management, Proceedings

ER -