CCM: A Text Classification Method by Clustering

Sarwat Nizamani, Nasrullah Memon, Uffe Kock Wiil, Panagiotis Karampelas

Publikation: Bidrag til bog/antologi/rapport/konference-proceedingKonferencebidrag i proceedingsForskningpeer review

Resumé

In this paper, a new Cluster based Classification Model (CCM) for suspicious email detection and other text classification tasks, is presented. Comparative experiments of the proposed model against traditional classification models and the boosting algorithm are also discussed. Experimental results show that the CCM outperforms traditional classification models as well as the boosting algorithm for the
task of suspicious email detection on terrorism domain email dataset and topic categorization on the Reuters-21578 and 20 Newsgroups datasets. The overall finding is that applying a cluster based
approach to text classification tasks simplifies the model and at the same time increases the accuracy.
OriginalsprogEngelsk
TitelASONAM 2011 : 2011 International Conference on Advances in Social Networks Analysis and Mining
RedaktørerD. Das, S. Bandyopadhyay
ForlagIEEE Computer Society Press
Publikationsdato2011
Sider461-467
ISBN (Elektronisk)978-0-7695-4375-8
StatusUdgivet - 2011

Fingeraftryk

Electronic mail
Terrorism
Experiments

Citer dette

Nizamani, S., Memon, N., Wiil, U. K., & Karampelas, P. (2011). CCM: A Text Classification Method by Clustering. I D. Das, & S. Bandyopadhyay (red.), ASONAM 2011: 2011 International Conference on Advances in Social Networks Analysis and Mining (s. 461-467). IEEE Computer Society Press.
Nizamani, Sarwat ; Memon, Nasrullah ; Wiil, Uffe Kock ; Karampelas, Panagiotis. / CCM: A Text Classification Method by Clustering. ASONAM 2011: 2011 International Conference on Advances in Social Networks Analysis and Mining. red. / D. Das ; S. Bandyopadhyay. IEEE Computer Society Press, 2011. s. 461-467
@inproceedings{08e884ff12804c7c8fa5c3a46cb17f58,
title = "CCM: A Text Classification Method by Clustering",
abstract = "In this paper, a new Cluster based Classification Model (CCM) for suspicious email detection and other text classification tasks, is presented. Comparative experiments of the proposed model against traditional classification models and the boosting algorithm are also discussed. Experimental results show that the CCM outperforms traditional classification models as well as the boosting algorithm for the task of suspicious email detection on terrorism domain email dataset and topic categorization on the Reuters-21578 and 20 Newsgroups datasets. The overall finding is that applying a cluster based approach to text classification tasks simplifies the model and at the same time increases the accuracy.",
author = "Sarwat Nizamani and Nasrullah Memon and Wiil, {Uffe Kock} and Panagiotis Karampelas",
year = "2011",
language = "English",
pages = "461--467",
editor = "D. Das and S. Bandyopadhyay",
booktitle = "ASONAM 2011",
publisher = "IEEE Computer Society Press",
address = "United States",

}

Nizamani, S, Memon, N, Wiil, UK & Karampelas, P 2011, CCM: A Text Classification Method by Clustering. i D Das & S Bandyopadhyay (red), ASONAM 2011: 2011 International Conference on Advances in Social Networks Analysis and Mining. IEEE Computer Society Press, s. 461-467.

CCM: A Text Classification Method by Clustering. / Nizamani, Sarwat; Memon, Nasrullah; Wiil, Uffe Kock; Karampelas, Panagiotis.

ASONAM 2011: 2011 International Conference on Advances in Social Networks Analysis and Mining. red. / D. Das; S. Bandyopadhyay. IEEE Computer Society Press, 2011. s. 461-467.

Publikation: Bidrag til bog/antologi/rapport/konference-proceedingKonferencebidrag i proceedingsForskningpeer review

TY - GEN

T1 - CCM: A Text Classification Method by Clustering

AU - Nizamani, Sarwat

AU - Memon, Nasrullah

AU - Wiil, Uffe Kock

AU - Karampelas, Panagiotis

PY - 2011

Y1 - 2011

N2 - In this paper, a new Cluster based Classification Model (CCM) for suspicious email detection and other text classification tasks, is presented. Comparative experiments of the proposed model against traditional classification models and the boosting algorithm are also discussed. Experimental results show that the CCM outperforms traditional classification models as well as the boosting algorithm for the task of suspicious email detection on terrorism domain email dataset and topic categorization on the Reuters-21578 and 20 Newsgroups datasets. The overall finding is that applying a cluster based approach to text classification tasks simplifies the model and at the same time increases the accuracy.

AB - In this paper, a new Cluster based Classification Model (CCM) for suspicious email detection and other text classification tasks, is presented. Comparative experiments of the proposed model against traditional classification models and the boosting algorithm are also discussed. Experimental results show that the CCM outperforms traditional classification models as well as the boosting algorithm for the task of suspicious email detection on terrorism domain email dataset and topic categorization on the Reuters-21578 and 20 Newsgroups datasets. The overall finding is that applying a cluster based approach to text classification tasks simplifies the model and at the same time increases the accuracy.

M3 - Article in proceedings

SP - 461

EP - 467

BT - ASONAM 2011

A2 - Das, D.

A2 - Bandyopadhyay, S.

PB - IEEE Computer Society Press

ER -

Nizamani S, Memon N, Wiil UK, Karampelas P. CCM: A Text Classification Method by Clustering. I Das D, Bandyopadhyay S, red., ASONAM 2011: 2011 International Conference on Advances in Social Networks Analysis and Mining. IEEE Computer Society Press. 2011. s. 461-467