An empirical comparison of fast and efficient tools for mining textual data

Volkan Tunali; A. Yılmaz Çamurcu; T. Tugay Bilgin

An empirical comparison of fast and efficient tools for mining textual data

Volkan Tunali^*, A. Yılmaz Çamurcu, T. Tugay Bilgin

^*Corresponding author for this work

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

Abstract

In order to effectively manage and retrieve the information comprised in vast amount of text documents, powerful text mining tools and techniques are essential. In this paper we evaluate and compare two state-of-the-art data mining tools for clustering high-dimensional text data, Cluto and Gmeans. Several experiments were conducted on three benchmark datasets, and results are analysed in terms of clustering quality, memory and CPU time consumption. We empirically show that Gmeans offers high scalability by sacrificing clustering quality while Cluto presents better clustering quality at the expense of memory and CPU time.

Original language	English
Title of host publication	1st International Symposium on Computing in Science & Engineering Proceedings
Place of Publication	Izmir, Turkey
Publisher	Gediz University Publications
Pages	141-147
Number of pages	7
ISBN (Electronic)	9786056139413
Publication status	Published - 3 Jun 2010
Externally published	Yes
Event	1st International Symposium on Computing in Science & Engineering - Kusadasi, Aydin, Turkey Duration: 3 Jun 2010 → 5 Jun 2010

Conference

Conference	1st International Symposium on Computing in Science & Engineering
Abbreviated title	ISCSE
Country/Territory	Turkey
City	Aydin
Period	3/06/10 → 5/06/10

Keywords

text mining
document clustering
spherical k-means
bisecting k-means

Cite this

@inproceedings{0f8920cd580a4f0db8a7b817ce2dde8c,

title = "An empirical comparison of fast and efficient tools for mining textual data",

abstract = "In order to effectively manage and retrieve the information comprised in vast amount of text documents, powerful text mining tools and techniques are essential. In this paper we evaluate and compare two state-of-the-art data mining tools for clustering high-dimensional text data, Cluto and Gmeans. Several experiments were conducted on three benchmark datasets, and results are analysed in terms of clustering quality, memory and CPU time consumption. We empirically show that Gmeans offers high scalability by sacrificing clustering quality while Cluto presents better clustering quality at the expense of memory and CPU time.",

keywords = "text mining, document clustering, spherical k-means, bisecting k-means",

author = "Volkan Tunali and {\c C}amurcu, \{A. Yılmaz\} and Bilgin, \{T. Tugay\}",

year = "2010",

month = jun,

day = "3",

language = "English",

pages = "141--147",

booktitle = "1st International Symposium on Computing in Science \& Engineering Proceedings",

publisher = "Gediz University Publications",

note = "1st International Symposium on Computing in Science \& Engineering, ISCSE ; Conference date: 03-06-2010 Through 05-06-2010",

}

An empirical comparison of fast and efficient tools for mining textual data. / Tunali, Volkan; Çamurcu, A. Yılmaz; Bilgin, T. Tugay.
1st International Symposium on Computing in Science & Engineering Proceedings. Izmir, Turkey: Gediz University Publications, 2010. p. 141-147.

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

TY - GEN

T1 - An empirical comparison of fast and efficient tools for mining textual data

AU - Tunali, Volkan

AU - Çamurcu, A. Yılmaz

AU - Bilgin, T. Tugay

PY - 2010/6/3

Y1 - 2010/6/3

N2 - In order to effectively manage and retrieve the information comprised in vast amount of text documents, powerful text mining tools and techniques are essential. In this paper we evaluate and compare two state-of-the-art data mining tools for clustering high-dimensional text data, Cluto and Gmeans. Several experiments were conducted on three benchmark datasets, and results are analysed in terms of clustering quality, memory and CPU time consumption. We empirically show that Gmeans offers high scalability by sacrificing clustering quality while Cluto presents better clustering quality at the expense of memory and CPU time.

AB - In order to effectively manage and retrieve the information comprised in vast amount of text documents, powerful text mining tools and techniques are essential. In this paper we evaluate and compare two state-of-the-art data mining tools for clustering high-dimensional text data, Cluto and Gmeans. Several experiments were conducted on three benchmark datasets, and results are analysed in terms of clustering quality, memory and CPU time consumption. We empirically show that Gmeans offers high scalability by sacrificing clustering quality while Cluto presents better clustering quality at the expense of memory and CPU time.

KW - text mining

KW - document clustering

KW - spherical k-means

KW - bisecting k-means

M3 - Conference contribution

SP - 141

EP - 147

BT - 1st International Symposium on Computing in Science & Engineering Proceedings

PB - Gediz University Publications

CY - Izmir, Turkey

T2 - 1st International Symposium on Computing in Science & Engineering

Y2 - 3 June 2010 through 5 June 2010

ER -

An empirical comparison of fast and efficient tools for mining textual data

Abstract

Conference

Keywords

Fingerprint

Cite this