Modeling Musical Influence with Topic Models

Uri Shalit; Daphna Weinshall; Gal Chechik

Modeling Musical Influence with Topic Models

Uri Shalit, Daphna Weinshall, Gal Chechik

Data and Decision Sciences

Technion - Israel Institute of Technology

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

Abstract

The role of musical influence has long been debated by scholars and critics in the humanities, but never in a data-driven way. In this work we approach the question of influence by applying topic-modeling tools (Blei & Lafferty, 2006; Gerrish & Blei, 2010) to a dataset of 24941 songs by 9222 artists, from the years 1922 to 2010. We find the models to be significantly correlated with a human-curated influence measure, and to clearly outperform a baseline method. Further using the learned model to study properties of influence, we find that musical influence and musical innovation are not monotonically correlated. However, we do find that the most influential songs were more innovative during two time periods: the early 1970’s and the mid 1990’s.

Original language	Undefined/Unknown
Title of host publication	Proceedings of the 30th International Conference on Machine Learning
Editors	Sanjoy Dasgupta, David McAllester
Place of Publication	Atlanta, Georgia, USA
Pages	244-252
Number of pages	9
Volume	28
State	Published - 1 May 2013

Publication series

Name	Proceedings of Machine Learning Research
Publisher	PMLR

Access to Document

https://proceedings.mlr.press/v28/shalit13.html

Cite this

@inproceedings{44c3044f816548659d4af3dc8e55f219,

title = "Modeling Musical Influence with Topic Models",

abstract = "The role of musical influence has long been debated by scholars and critics in the humanities, but never in a data-driven way. In this work we approach the question of influence by applying topic-modeling tools (Blei & Lafferty, 2006; Gerrish & Blei, 2010) to a dataset of 24941 songs by 9222 artists, from the years 1922 to 2010. We find the models to be significantly correlated with a human-curated influence measure, and to clearly outperform a baseline method. Further using the learned model to study properties of influence, we find that musical influence and musical innovation are not monotonically correlated. However, we do find that the most influential songs were more innovative during two time periods: the early 1970{\textquoteright}s and the mid 1990{\textquoteright}s.",

author = "Uri Shalit and Daphna Weinshall and Gal Chechik",

year = "2013",

month = may,

day = "1",

language = "!!Undefined/Unknown",

volume = "28",

series = "Proceedings of Machine Learning Research",

publisher = "PMLR",

pages = "244--252",

editor = "Sanjoy Dasgupta and David McAllester",

booktitle = "Proceedings of the 30th International Conference on Machine Learning",

}

Modeling Musical Influence with Topic Models. / Shalit, Uri; Weinshall, Daphna; Chechik, Gal.
Proceedings of the 30th International Conference on Machine Learning. ed. / Sanjoy Dasgupta; David McAllester. Vol. 28 Atlanta, Georgia, USA, 2013. p. 244-252 (Proceedings of Machine Learning Research).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Modeling Musical Influence with Topic Models

AU - Shalit, Uri

AU - Weinshall, Daphna

AU - Chechik, Gal

PY - 2013/5/1

Y1 - 2013/5/1

N2 - The role of musical influence has long been debated by scholars and critics in the humanities, but never in a data-driven way. In this work we approach the question of influence by applying topic-modeling tools (Blei & Lafferty, 2006; Gerrish & Blei, 2010) to a dataset of 24941 songs by 9222 artists, from the years 1922 to 2010. We find the models to be significantly correlated with a human-curated influence measure, and to clearly outperform a baseline method. Further using the learned model to study properties of influence, we find that musical influence and musical innovation are not monotonically correlated. However, we do find that the most influential songs were more innovative during two time periods: the early 1970’s and the mid 1990’s.

AB - The role of musical influence has long been debated by scholars and critics in the humanities, but never in a data-driven way. In this work we approach the question of influence by applying topic-modeling tools (Blei & Lafferty, 2006; Gerrish & Blei, 2010) to a dataset of 24941 songs by 9222 artists, from the years 1922 to 2010. We find the models to be significantly correlated with a human-curated influence measure, and to clearly outperform a baseline method. Further using the learned model to study properties of influence, we find that musical influence and musical innovation are not monotonically correlated. However, we do find that the most influential songs were more innovative during two time periods: the early 1970’s and the mid 1990’s.

M3 - منشور من مؤتمر

VL - 28

T3 - Proceedings of Machine Learning Research

SP - 244

EP - 252

BT - Proceedings of the 30th International Conference on Machine Learning

A2 - Dasgupta, Sanjoy

A2 - McAllester, David

CY - Atlanta, Georgia, USA

ER -