A simple mixture model for unsupervised text categorisation

F. Clérot; F. Fessant; O. Collin; O. Cappé; E. Moulines

A simple mixture model for unsupervised text categorisation

F. Clérot, F. Fessant, O. Collin, O. Cappé, E. Moulines

Research output: Contribution to journal › Conference article › peer-review

Abstract

Automatically segmenting text corpora into thematically related groups is a complex exploratory analysis problem. In this article, we outline our multi-stage exploratory analysis process and investigate the performance of a simple statistical model. After a description of this model and of its fitting procedure, we illustrate its performance on the segmentation of a corpus of CKM-related texts in English.

Original language	English
Pages (from-to)	13-22
Number of pages	10
Journal	Management Information Systems
Volume	10
Publication status	Published - 1 Dec 2004
Event	Fifth International Conference on Data Mining, DATA MINING V - Malaga, Spain Duration: 15 Sept 2004 → 17 Sept 2004

Keywords

Clustering
Exploratory analysis
Mixture model
Text mining

Cite this

@article{b366a0ef10194b3c9711ec93d7c7f6ce,

title = "A simple mixture model for unsupervised text categorisation",

abstract = "Automatically segmenting text corpora into thematically related groups is a complex exploratory analysis problem. In this article, we outline our multi-stage exploratory analysis process and investigate the performance of a simple statistical model. After a description of this model and of its fitting procedure, we illustrate its performance on the segmentation of a corpus of CKM-related texts in English.",

keywords = "Clustering, Exploratory analysis, Mixture model, Text mining",

author = "F. Cl{\'e}rot and F. Fessant and O. Collin and O. Capp{\'e} and E. Moulines",

year = "2004",

month = dec,

day = "1",

language = "English",

volume = "10",

pages = "13--22",

journal = "Management Information Systems",

issn = "1470-6326",

note = "Fifth International Conference on Data Mining, DATA MINING V ; Conference date: 15-09-2004 Through 17-09-2004",

}

TY - JOUR

T1 - A simple mixture model for unsupervised text categorisation

AU - Clérot, F.

AU - Fessant, F.

AU - Collin, O.

AU - Cappé, O.

AU - Moulines, E.

PY - 2004/12/1

Y1 - 2004/12/1

N2 - Automatically segmenting text corpora into thematically related groups is a complex exploratory analysis problem. In this article, we outline our multi-stage exploratory analysis process and investigate the performance of a simple statistical model. After a description of this model and of its fitting procedure, we illustrate its performance on the segmentation of a corpus of CKM-related texts in English.

AB - Automatically segmenting text corpora into thematically related groups is a complex exploratory analysis problem. In this article, we outline our multi-stage exploratory analysis process and investigate the performance of a simple statistical model. After a description of this model and of its fitting procedure, we illustrate its performance on the segmentation of a corpus of CKM-related texts in English.

KW - Clustering

KW - Exploratory analysis

KW - Mixture model

KW - Text mining

M3 - Conference article

AN - SCOPUS:11844270561

SN - 1470-6326

VL - 10

SP - 13

EP - 22

JO - Management Information Systems

JF - Management Information Systems

T2 - Fifth International Conference on Data Mining, DATA MINING V

Y2 - 15 September 2004 through 17 September 2004

ER -

A simple mixture model for unsupervised text categorisation

Abstract

Keywords

Fingerprint

Cite this