Oh Oh Oh Whoah! Towards Automatic Topic Detection in Song Lyrics.

Florian Kleedorfer; Tim Pohle; Peter Knees

Oh Oh Oh Whoah! Towards Automatic Topic Detection in Song Lyrics.

Florian Kleedorfer
, Tim Pohle
, Peter Knees

Institute of Computational Perception

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

Abstract

We present an algorithm that allows for indexing music by topic. The application scenario is an information retrieval system into which any song with known lyrics can be inserted and indexed so as to make a music collection browseable by topic. We use text mining techniques for creating a vector space model of our lyrics collection and non-negative matrix factorization (NMF) to identify topic clusters which are then labeled manually. We include a discussion of the decisions regarding the parametrization of the applied methods. The suitability of our approach is assessed by measuring the agreement of test subjects who provide the labels for the topic clusters.

Original language	English
Title of host publication	Proceedings of the 9th International Conference on Music Information Retrieval (ISMIR 2008), Philadelphia, PA, USA.
Number of pages	6
Publication status	Published - 2008

Fields of science

102 Computer Sciences
102001 Artificial intelligence
102003 Image processing
102015 Information systems
202002 Audiovisual media

Cite this

@inproceedings{cd8ee8fb7ee049139eca3d6e02aacd94,

title = "Oh Oh Oh Whoah! Towards Automatic Topic Detection in Song Lyrics.",

abstract = "We present an algorithm that allows for indexing music by topic. The application scenario is an information retrieval system into which any song with known lyrics can be inserted and indexed so as to make a music collection browseable by topic. We use text mining techniques for creating a vector space model of our lyrics collection and non-negative matrix factorization (NMF) to identify topic clusters which are then labeled manually. We include a discussion of the decisions regarding the parametrization of the applied methods. The suitability of our approach is assessed by measuring the agreement of test subjects who provide the labels for the topic clusters.",

author = "Florian Kleedorfer and Tim Pohle and Peter Knees",

year = "2008",

language = "English",

booktitle = "Proceedings of the 9th International Conference on Music Information Retrieval (ISMIR 2008), Philadelphia, PA, USA.",

}

TY - GEN

T1 - Oh Oh Oh Whoah! Towards Automatic Topic Detection in Song Lyrics.

AU - Kleedorfer, Florian

AU - Pohle, Tim

AU - Knees, Peter

PY - 2008

Y1 - 2008

N2 - We present an algorithm that allows for indexing music by topic. The application scenario is an information retrieval system into which any song with known lyrics can be inserted and indexed so as to make a music collection browseable by topic. We use text mining techniques for creating a vector space model of our lyrics collection and non-negative matrix factorization (NMF) to identify topic clusters which are then labeled manually. We include a discussion of the decisions regarding the parametrization of the applied methods. The suitability of our approach is assessed by measuring the agreement of test subjects who provide the labels for the topic clusters.

AB - We present an algorithm that allows for indexing music by topic. The application scenario is an information retrieval system into which any song with known lyrics can be inserted and indexed so as to make a music collection browseable by topic. We use text mining techniques for creating a vector space model of our lyrics collection and non-negative matrix factorization (NMF) to identify topic clusters which are then labeled manually. We include a discussion of the decisions regarding the parametrization of the applied methods. The suitability of our approach is assessed by measuring the agreement of test subjects who provide the labels for the topic clusters.

M3 - Conference proceedings

BT - Proceedings of the 9th International Conference on Music Information Retrieval (ISMIR 2008), Philadelphia, PA, USA.

ER -