Hierarchical co-clustering of music artists and tags

Jingxuan Li, Tao Li, Mitsunori Ogihara

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

2 Citations (Scopus)

Abstract

The user-assigned tag is a growingly important research topic in MIR. Noticing that some tags are more specific versions of others, this paper studies the problem of organizing tags into a hierarchical structure by taking into ac- count the fact that the corresponding artists are organized into a hierarchy based on genre and style. A novel clustering algorithm, Hierarchical Co-clustering Algorithm (HCC), is proposed as a solution. Unlike traditional hierarchical clustering algorithms that deal with homogeneous data only, the proposed algorithm simultaneously organizes two distinct data types into hierarchies. HCC is additionally able to receive constraints that state certain objects "must-be-together" or "should-be-together" and build clusters so as to satisfying the constraints. HCC may lead to better and deeper understandings of relationship between artists and tags assigned to them. An experiment finds that by trying to hierarchically cluster the two types of data better clusters are obtained for both. It is also shown that HCC is able to incorporate instance-level constraints on artists and/or tags to improve the clustering process.

Original languageEnglish (US)
Title of host publicationProceedings of the 11th International Society for Music Information Retrieval Conference, ISMIR 2010
Pages249-254
Number of pages6
StatePublished - 2010
Event11th International Society for Music Information Retrieval Conference, ISMIR 2010 - Utrecht, Netherlands
Duration: Aug 9 2010Aug 13 2010

Other

Other11th International Society for Music Information Retrieval Conference, ISMIR 2010
CountryNetherlands
CityUtrecht
Period8/9/108/13/10

Fingerprint

Clustering algorithms
Artist
Tag
Music
Experiments

ASJC Scopus subject areas

  • Music
  • Information Systems

Cite this

Li, J., Li, T., & Ogihara, M. (2010). Hierarchical co-clustering of music artists and tags. In Proceedings of the 11th International Society for Music Information Retrieval Conference, ISMIR 2010 (pp. 249-254)

Hierarchical co-clustering of music artists and tags. / Li, Jingxuan; Li, Tao; Ogihara, Mitsunori.

Proceedings of the 11th International Society for Music Information Retrieval Conference, ISMIR 2010. 2010. p. 249-254.

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

Li, J, Li, T & Ogihara, M 2010, Hierarchical co-clustering of music artists and tags. in Proceedings of the 11th International Society for Music Information Retrieval Conference, ISMIR 2010. pp. 249-254, 11th International Society for Music Information Retrieval Conference, ISMIR 2010, Utrecht, Netherlands, 8/9/10.
Li J, Li T, Ogihara M. Hierarchical co-clustering of music artists and tags. In Proceedings of the 11th International Society for Music Information Retrieval Conference, ISMIR 2010. 2010. p. 249-254
Li, Jingxuan ; Li, Tao ; Ogihara, Mitsunori. / Hierarchical co-clustering of music artists and tags. Proceedings of the 11th International Society for Music Information Retrieval Conference, ISMIR 2010. 2010. pp. 249-254
@inproceedings{69611787e0f741cfa9caeb09bb485d76,
title = "Hierarchical co-clustering of music artists and tags",
abstract = "The user-assigned tag is a growingly important research topic in MIR. Noticing that some tags are more specific versions of others, this paper studies the problem of organizing tags into a hierarchical structure by taking into ac- count the fact that the corresponding artists are organized into a hierarchy based on genre and style. A novel clustering algorithm, Hierarchical Co-clustering Algorithm (HCC), is proposed as a solution. Unlike traditional hierarchical clustering algorithms that deal with homogeneous data only, the proposed algorithm simultaneously organizes two distinct data types into hierarchies. HCC is additionally able to receive constraints that state certain objects {"}must-be-together{"} or {"}should-be-together{"} and build clusters so as to satisfying the constraints. HCC may lead to better and deeper understandings of relationship between artists and tags assigned to them. An experiment finds that by trying to hierarchically cluster the two types of data better clusters are obtained for both. It is also shown that HCC is able to incorporate instance-level constraints on artists and/or tags to improve the clustering process.",
author = "Jingxuan Li and Tao Li and Mitsunori Ogihara",
year = "2010",
language = "English (US)",
isbn = "9789039353813",
pages = "249--254",
booktitle = "Proceedings of the 11th International Society for Music Information Retrieval Conference, ISMIR 2010",

}

TY - GEN

T1 - Hierarchical co-clustering of music artists and tags

AU - Li, Jingxuan

AU - Li, Tao

AU - Ogihara, Mitsunori

PY - 2010

Y1 - 2010

N2 - The user-assigned tag is a growingly important research topic in MIR. Noticing that some tags are more specific versions of others, this paper studies the problem of organizing tags into a hierarchical structure by taking into ac- count the fact that the corresponding artists are organized into a hierarchy based on genre and style. A novel clustering algorithm, Hierarchical Co-clustering Algorithm (HCC), is proposed as a solution. Unlike traditional hierarchical clustering algorithms that deal with homogeneous data only, the proposed algorithm simultaneously organizes two distinct data types into hierarchies. HCC is additionally able to receive constraints that state certain objects "must-be-together" or "should-be-together" and build clusters so as to satisfying the constraints. HCC may lead to better and deeper understandings of relationship between artists and tags assigned to them. An experiment finds that by trying to hierarchically cluster the two types of data better clusters are obtained for both. It is also shown that HCC is able to incorporate instance-level constraints on artists and/or tags to improve the clustering process.

AB - The user-assigned tag is a growingly important research topic in MIR. Noticing that some tags are more specific versions of others, this paper studies the problem of organizing tags into a hierarchical structure by taking into ac- count the fact that the corresponding artists are organized into a hierarchy based on genre and style. A novel clustering algorithm, Hierarchical Co-clustering Algorithm (HCC), is proposed as a solution. Unlike traditional hierarchical clustering algorithms that deal with homogeneous data only, the proposed algorithm simultaneously organizes two distinct data types into hierarchies. HCC is additionally able to receive constraints that state certain objects "must-be-together" or "should-be-together" and build clusters so as to satisfying the constraints. HCC may lead to better and deeper understandings of relationship between artists and tags assigned to them. An experiment finds that by trying to hierarchically cluster the two types of data better clusters are obtained for both. It is also shown that HCC is able to incorporate instance-level constraints on artists and/or tags to improve the clustering process.

UR - http://www.scopus.com/inward/record.url?scp=84873597367&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84873597367&partnerID=8YFLogxK

M3 - Conference contribution

SN - 9789039353813

SP - 249

EP - 254

BT - Proceedings of the 11th International Society for Music Information Retrieval Conference, ISMIR 2010

ER -