A PSO-based clustering approach assisted by initial clustering information

Clustering of short texts is an important research area because of its applicability in information retrieval and text mining. To this end was proposed CLUDIPSO, a discrete Particle Swarm Optimization algorithm to cluster short texts. Initial results showed that CLUDIPSO has performed well in small...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Velázquez, Carlos, Cagnina, Leticia, Errecalde, Marcelo Luis
Formato:	Objeto de conferencia
Lenguaje:	Inglés
Publicado:	2012
Materias:	Ciencias Informáticas Short-Text Clustering Bio-Inspired Methods PSO-based Clustering Hybrid Methods Expectation-Maximization Initialization Approaches Clustering base de datos Data mining
Acceso en línea:	http://sedici.unlp.edu.ar/handle/10915/23753
Aporte de:	SEDICI (UNLP) de Universidad Nacional de La Plata

id	I19-R120-10915-23753
record_format	dspace
institution	Universidad Nacional de La Plata
institution_str	I-19
repository_str	R-120
collection	SEDICI (UNLP)
language	Inglés
topic	Ciencias Informáticas Short-Text Clustering Bio-Inspired Methods PSO-based Clustering Hybrid Methods Expectation-Maximization Initialization Approaches Clustering base de datos Data mining
spellingShingle	Ciencias Informáticas Short-Text Clustering Bio-Inspired Methods PSO-based Clustering Hybrid Methods Expectation-Maximization Initialization Approaches Clustering base de datos Data mining Velázquez, Carlos Cagnina, Leticia Errecalde, Marcelo Luis A PSO-based clustering approach assisted by initial clustering information
topic_facet	Ciencias Informáticas Short-Text Clustering Bio-Inspired Methods PSO-based Clustering Hybrid Methods Expectation-Maximization Initialization Approaches Clustering base de datos Data mining
description	Clustering of short texts is an important research area because of its applicability in information retrieval and text mining. To this end was proposed CLUDIPSO, a discrete Particle Swarm Optimization algorithm to cluster short texts. Initial results showed that CLUDIPSO has performed well in small collections of short texts. However, later works showed some drawbacks when dealing with larger collections. In this paper we present a hybridization of CLUDIPSO to overcome these drawbacks, by providing information in the initial cycles of the algorithm to avoid a random search and thus speed up the convergence process. This is achieved by using a pre-clustering obtained with the Expectation-Maximization method which is included in the initial population of the algorithm. The results obtained with the hybrid version show a significant improvement over those obtained with the original version.
format	Objeto de conferencia Objeto de conferencia
author	Velázquez, Carlos Cagnina, Leticia Errecalde, Marcelo Luis
author_facet	Velázquez, Carlos Cagnina, Leticia Errecalde, Marcelo Luis
author_sort	Velázquez, Carlos
title	A PSO-based clustering approach assisted by initial clustering information
title_short	A PSO-based clustering approach assisted by initial clustering information
title_full	A PSO-based clustering approach assisted by initial clustering information
title_fullStr	A PSO-based clustering approach assisted by initial clustering information
title_full_unstemmed	A PSO-based clustering approach assisted by initial clustering information
title_sort	pso-based clustering approach assisted by initial clustering information
publishDate	2012
url	http://sedici.unlp.edu.ar/handle/10915/23753
work_keys_str_mv	AT velazquezcarlos apsobasedclusteringapproachassistedbyinitialclusteringinformation AT cagninaleticia apsobasedclusteringapproachassistedbyinitialclusteringinformation AT errecaldemarceloluis apsobasedclusteringapproachassistedbyinitialclusteringinformation AT velazquezcarlos psobasedclusteringapproachassistedbyinitialclusteringinformation AT cagninaleticia psobasedclusteringapproachassistedbyinitialclusteringinformation AT errecaldemarceloluis psobasedclusteringapproachassistedbyinitialclusteringinformation
bdutipo_str	Repositorios
_version_	1764820466165350403

A PSO-based clustering approach assisted by initial clustering information

Ejemplares similares