There is a wide set of evaluation metrics available to compare the quality of text clustering algorithms. In this article, we define a few intuitive formal constraints on such metrics which shed light on which aspects of the quality of a clustering are captured by different metric families. These formal constraints are validated in an experiment involving human assessments, and compared with other constraints proposed in the literature. Our analysis of a wide range of metrics shows that only BCubed satisfies all formal constraints. We also extend the analysis to the problem of overlapping clustering, where items can simultaneously belong to more than one cluster. As Bcubed cannot be directly applied to this task, we propose a modified version of Bcubed that avoids the problems found with other metrics.
:Users/julien.gaugaz/Dropbox/Papers/Mendeley Desktop/2008/Amigó et al. - 2008 - A comparison of extrinsic clustering evaluation metrics based on formal constraints.pdf:pdf
%0 Journal Article
%1 Amigo2008
%A Amigó, Enrique
%A Gonzalo, Julio
%A Artiles, Javier
%A Verdejo, Felisa
%D 2008
%I Springer Netherlands
%J Inf. Retr. Boston.
%K Computer_Science evaluation phd
%N 4
%P 461--486
%R 10.1007/s10791-008-9066-8
%T A comparison of extrinsic clustering evaluation metrics based on formal constraints
%U http://www.springerlink.com/content/812x06387l52p045/
%V 12
%X There is a wide set of evaluation metrics available to compare the quality of text clustering algorithms. In this article, we define a few intuitive formal constraints on such metrics which shed light on which aspects of the quality of a clustering are captured by different metric families. These formal constraints are validated in an experiment involving human assessments, and compared with other constraints proposed in the literature. Our analysis of a wide range of metrics shows that only BCubed satisfies all formal constraints. We also extend the analysis to the problem of overlapping clustering, where items can simultaneously belong to more than one cluster. As Bcubed cannot be directly applied to this task, we propose a modified version of Bcubed that avoids the problems found with other metrics.
@article{Amigo2008,
abstract = {There is a wide set of evaluation metrics available to compare the quality of text clustering algorithms. In this article, we define a few intuitive formal constraints on such metrics which shed light on which aspects of the quality of a clustering are captured by different metric families. These formal constraints are validated in an experiment involving human assessments, and compared with other constraints proposed in the literature. Our analysis of a wide range of metrics shows that only BCubed satisfies all formal constraints. We also extend the analysis to the problem of overlapping clustering, where items can simultaneously belong to more than one cluster. As Bcubed cannot be directly applied to this task, we propose a modified version of Bcubed that avoids the problems found with other metrics.},
added-at = {2013-12-17T10:08:37.000+0100},
author = {Amig\'{o}, Enrique and Gonzalo, Julio and Artiles, Javier and Verdejo, Felisa},
biburl = {https://www.bibsonomy.org/bibtex/2bf5389827876132d05a0e73c662fbca4/jullybobble},
doi = {10.1007/s10791-008-9066-8},
file = {:Users/julien.gaugaz/Dropbox/Papers/Mendeley Desktop/2008/Amig\'{o} et al. - 2008 - A comparison of extrinsic clustering evaluation metrics based on formal constraints.pdf:pdf},
interhash = {a91f82561cb72ae5bcf05e5de56ea1bc},
intrahash = {bf5389827876132d05a0e73c662fbca4},
issn = {1386-4564},
journal = {Inf. Retr. Boston.},
keywords = {Computer_Science evaluation phd},
mendeley-tags = {evaluation},
month = jul,
number = 4,
pages = {461--486},
publisher = {Springer Netherlands},
timestamp = {2014-07-27T15:43:19.000+0200},
title = {{A comparison of extrinsic clustering evaluation metrics based on formal constraints}},
url = {http://www.springerlink.com/content/812x06387l52p045/},
volume = 12,
year = 2008
}