Topics in 0--1 data

Ella Bingham; H. Mannila; J.K. Seppänen

doi:10.1145/775047.775112

Topics in 0--1 data

Tutkimustuotos: Artikkeli kirjassa/konferenssijulkaisussa › Conference article in proceedings › Scientific › vertaisarvioitu

3 Sitaatiot (Scopus)

Abstrakti

Large 0--1 datasets arise in various applications, such as market basket analysis and information retrieval. We concentrate on the study of topic models, aiming at results which indicate why certain methods succeed or fail. We describe simple algorithms for finding topic models from 0--1 data. We give theoretical results showing that the algorithms can discover the epsilon-separable topic models of Papadimitriou et al. We present empirical results showing that the algorithms find natural topics in real-world data sets. We also briefly discuss the connections to matrix approaches, including nonnegative matrix factorization and independent component analysis.

Alkuperäiskieli	Englanti
Otsikko	KDD '02: Proceedings of the eighth ACM SIGKDD International Conference on Knowledge Discovery and Data Mining
Kustantaja	ACM
Sivut	450-455
ISBN (elektroninen)	978-1-58113-567-1
DOI - pysyväislinkit	https://doi.org/10.1145/775047.775112
Tila	Julkaistu - 2002
OKM-julkaisutyyppi	A4 Artikkeli konferenssijulkaisussa
Tapahtuma	ACM SIGKDD International Conference on Knowledge Discovery and Data Mining - Edmonton, Kanada Kesto: 23 kesäk. 2002 → 26 kesäk. 2002 Konferenssinumero: 8

Conference

Conference	ACM SIGKDD International Conference on Knowledge Discovery and Data Mining
Lyhennettä	KDD
Maa/Alue	Kanada
Kaupunki	Edmonton
Ajanjakso	23/06/2002 → 26/06/2002

Tutkimusalat

0-1 data
data mining
latent variable model
topic models

Pääsy asiakirjaan

10.1145/775047.775112

Siteeraa tätä

@inproceedings{0dfbf81562974386b34fa543684c68e7,

title = "Topics in 0--1 data",

abstract = "Large 0--1 datasets arise in various applications, such as market basket analysis and information retrieval. We concentrate on the study of topic models, aiming at results which indicate why certain methods succeed or fail. We describe simple algorithms for finding topic models from 0--1 data. We give theoretical results showing that the algorithms can discover the epsilon-separable topic models of Papadimitriou et al. We present empirical results showing that the algorithms find natural topics in real-world data sets. We also briefly discuss the connections to matrix approaches, including nonnegative matrix factorization and independent component analysis.",

keywords = "0-1 data, data mining, latent variable model, topic models, 0-1 data, data mining, latent variable model, topic models, 0-1 data, data mining, latent variable model, topic models",

author = "Ella Bingham and H. Mannila and J.K. Sepp{\"a}nen",

year = "2002",

doi = "10.1145/775047.775112",

language = "English",

pages = "450--455",

booktitle = "KDD '02: Proceedings of the eighth ACM SIGKDD International Conference on Knowledge Discovery and Data Mining",

publisher = "ACM",

address = "United States",

note = "ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, KDD ; Conference date: 23-06-2002 Through 26-06-2002",

}

TY - GEN

T1 - Topics in 0--1 data

AU - Bingham, Ella

AU - Mannila, H.

AU - Seppänen, J.K.

N1 - Conference code: 8

PY - 2002

Y1 - 2002

N2 - Large 0--1 datasets arise in various applications, such as market basket analysis and information retrieval. We concentrate on the study of topic models, aiming at results which indicate why certain methods succeed or fail. We describe simple algorithms for finding topic models from 0--1 data. We give theoretical results showing that the algorithms can discover the epsilon-separable topic models of Papadimitriou et al. We present empirical results showing that the algorithms find natural topics in real-world data sets. We also briefly discuss the connections to matrix approaches, including nonnegative matrix factorization and independent component analysis.

AB - Large 0--1 datasets arise in various applications, such as market basket analysis and information retrieval. We concentrate on the study of topic models, aiming at results which indicate why certain methods succeed or fail. We describe simple algorithms for finding topic models from 0--1 data. We give theoretical results showing that the algorithms can discover the epsilon-separable topic models of Papadimitriou et al. We present empirical results showing that the algorithms find natural topics in real-world data sets. We also briefly discuss the connections to matrix approaches, including nonnegative matrix factorization and independent component analysis.

KW - 0-1 data

KW - data mining

KW - latent variable model

KW - topic models

KW - 0-1 data

KW - data mining

KW - latent variable model

KW - topic models

KW - 0-1 data

KW - data mining

KW - latent variable model

KW - topic models

U2 - 10.1145/775047.775112

DO - 10.1145/775047.775112

M3 - Conference article in proceedings

SP - 450

EP - 455

BT - KDD '02: Proceedings of the eighth ACM SIGKDD International Conference on Knowledge Discovery and Data Mining

PB - ACM

T2 - ACM SIGKDD International Conference on Knowledge Discovery and Data Mining

Y2 - 23 June 2002 through 26 June 2002

ER -

Topics in 0--1 data

Abstrakti

Conference

Tutkimusalat

Pääsy asiakirjaan

Sormenjälki

Siteeraa tätä