Temporal analysis of text data using latent variable models

Lasse Lohilahti Mølgaard; Jan Larsen; Cyril Goutte

doi:10.1109/MLSP.2009.5306265

Temporal analysis of text data using latent variable models

Lasse Lohilahti Mølgaard, Jan Larsen, Cyril Goutte

National Research Council of Canada

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

811 Downloads (Pure)

Abstract

Detecting and tracking of temporal data is an important task in multiple applications. In this paper we study temporal text mining methods for Music Information Retrieval. We compare two ways of detecting the temporal latent semantics of a corpus extracted from Wikipedia, using a stepwise Probabilistic Latent Semantic Analysis (PLSA) approach and a global multiway PLSA method. The analysis indicates that the global analysis method is able to identify relevant trends which are difficult to get using a step-by-step approach. Furthermore we show that inspection of PLSA models with different number of factors may reveal the stability of temporal clusters making it possible to choose the relevant number of factors.

Original language	English
Title of host publication	2009 IEEE International Workshop on MACHINE LEARNING FOR SIGNAL PROCESSING. : Formerly the IEEE Workshop on Neural Networks for Signal Processing
Publisher	IEEE
Publication date	2009
ISBN (Print)	978-1-4244-4947-7
DOIs	https://doi.org/10.1109/MLSP.2009.5306265
Publication status	Published - 2009
Event	2009 IEEE International Workshop on Machine Learning for Signal Processing - Grenoble, France Duration: 1 Sept 2009 → 4 Sept 2009 Conference number: 19 https://ieeexplore.ieee.org/xpl/conhome/5290615/proceeding

Workshop

Workshop	2009 IEEE International Workshop on Machine Learning for Signal Processing
Number	19
Country/Territory	France
City	Grenoble
Period	01/09/2009 → 04/09/2009
Internet address	https://ieeexplore.ieee.org/xpl/conhome/5290615/proceeding

Bibliographical note

Copyright 2009 IEEE. Personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works must be obtained from the IEEE.

Access to Document

10.1109/MLSP.2009.5306265

M lgaardFinal published version, 4.11 MB
Mlsp molgaard1

OpenUrl availability

Full text

Cite this

@inproceedings{0afea7e436bf4d16b54a70cfc728835e,

title = "Temporal analysis of text data using latent variable models",

abstract = "Detecting and tracking of temporal data is an important task in multiple applications. In this paper we study temporal text mining methods for Music Information Retrieval. We compare two ways of detecting the temporal latent semantics of a corpus extracted from Wikipedia, using a stepwise Probabilistic Latent Semantic Analysis (PLSA) approach and a global multiway PLSA method. The analysis indicates that the global analysis method is able to identify relevant trends which are difficult to get using a step-by-step approach. Furthermore we show that inspection of PLSA models with different number of factors may reveal the stability of temporal clusters making it possible to choose the relevant number of factors.",

author = "M{\o}lgaard, {Lasse Lohilahti} and Jan Larsen and Cyril Goutte",

note = "Copyright 2009 IEEE. Personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works must be obtained from the IEEE.; 2009 IEEE International Workshop on Machine Learning for Signal Processing, MLSP 2009 ; Conference date: 01-09-2009 Through 04-09-2009",

year = "2009",

doi = "10.1109/MLSP.2009.5306265",

language = "English",

isbn = "978-1-4244-4947-7",

booktitle = "2009 IEEE International Workshop on MACHINE LEARNING FOR SIGNAL PROCESSING.",

publisher = "IEEE",

address = "United States",

url = "https://ieeexplore.ieee.org/xpl/conhome/5290615/proceeding",

}

Mølgaard, LL, Larsen, J & Goutte, C 2009, Temporal analysis of text data using latent variable models. in 2009 IEEE International Workshop on MACHINE LEARNING FOR SIGNAL PROCESSING.: Formerly the IEEE Workshop on Neural Networks for Signal Processing. IEEE, 2009 IEEE International Workshop on Machine Learning for Signal Processing, Grenoble, France, 01/09/2009. https://doi.org/10.1109/MLSP.2009.5306265

Temporal analysis of text data using latent variable models. / Mølgaard, Lasse Lohilahti; Larsen, Jan; Goutte, Cyril.
2009 IEEE International Workshop on MACHINE LEARNING FOR SIGNAL PROCESSING.: Formerly the IEEE Workshop on Neural Networks for Signal Processing. IEEE, 2009.

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

TY - GEN

T1 - Temporal analysis of text data using latent variable models

AU - Mølgaard, Lasse Lohilahti

AU - Larsen, Jan

AU - Goutte, Cyril

N1 - Conference code: 19

PY - 2009

Y1 - 2009

N2 - Detecting and tracking of temporal data is an important task in multiple applications. In this paper we study temporal text mining methods for Music Information Retrieval. We compare two ways of detecting the temporal latent semantics of a corpus extracted from Wikipedia, using a stepwise Probabilistic Latent Semantic Analysis (PLSA) approach and a global multiway PLSA method. The analysis indicates that the global analysis method is able to identify relevant trends which are difficult to get using a step-by-step approach. Furthermore we show that inspection of PLSA models with different number of factors may reveal the stability of temporal clusters making it possible to choose the relevant number of factors.

AB - Detecting and tracking of temporal data is an important task in multiple applications. In this paper we study temporal text mining methods for Music Information Retrieval. We compare two ways of detecting the temporal latent semantics of a corpus extracted from Wikipedia, using a stepwise Probabilistic Latent Semantic Analysis (PLSA) approach and a global multiway PLSA method. The analysis indicates that the global analysis method is able to identify relevant trends which are difficult to get using a step-by-step approach. Furthermore we show that inspection of PLSA models with different number of factors may reveal the stability of temporal clusters making it possible to choose the relevant number of factors.

U2 - 10.1109/MLSP.2009.5306265

DO - 10.1109/MLSP.2009.5306265

M3 - Article in proceedings

SN - 978-1-4244-4947-7

BT - 2009 IEEE International Workshop on MACHINE LEARNING FOR SIGNAL PROCESSING.

PB - IEEE

T2 - 2009 IEEE International Workshop on Machine Learning for Signal Processing

Y2 - 1 September 2009 through 4 September 2009

ER -

Temporal analysis of text data using latent variable models

Abstract

Workshop

Bibliographical note

Access to Document

OpenUrl availability

Fingerprint

Cite this