A spam filtering multi-objective optimization study covering parsimony maximization and three-way classification

Basto-Fernandes, Vitor; Yevseyeva, Iryna; Méndez, José R.; Zhao, Jiaqi; Fdez-Riverola, Florentino; Emmerich, Michael T.M.

Publication

A spam filtering multi-objective optimization study covering parsimony maximization and three-way classification

2016-11Journal article

dc.contributor.author	Basto-Fernandes, Vitor
dc.contributor.author	Yevseyeva, Iryna
dc.contributor.author	Méndez, José R.
dc.contributor.author	Zhao, Jiaqi
dc.contributor.author	Fdez-Riverola, Florentino
dc.contributor.author	Emmerich, Michael T.M.
dc.date.accessioned	2025-05-27T10:04:00Z
dc.date.available	2025-05-27T10:04:00Z
dc.date.issued	2016-11
dc.description.abstract	Classifier performance optimization in machine learning can be stated as a multi-objective optimization problem. In this context, recent works have shown the utility of simple evolutionary multi-objective algorithms (NSGA-II, SPEA2) to conveniently optimize the global performance of different anti-spam filters. The present work extends existing contributions in the spam filtering domain by using three novel indicator-based (SMS-EMOA, CH-EMOA) and decomposition-based (MOEA/D) evolutionary multiobjective algorithms. The proposed approaches are used to optimize the performance of a heterogeneous ensemble of classifiers into two different but complementary scenarios: parsimony maximization and e-mail classification under low confidence level. Experimental results using a publicly available standard corpus allowed us to identify interesting conclusions regarding both the utility of rule-based classification filters and the appropriateness of a three-way classification system in the spam filtering domain.	eng
dc.description.sponsorship	This work has been partially funded by the [14VI05] Contract-Programme from the University of Vigo. SING group thanks CITI (Centro de Investigación, Transferencia e Innovación) from University of Vigo for hosting its IT infrastructure. The authors would like to thank Pu Wang for sharing the code of CH-MOGP.
dc.identifier.citation	Vitor Basto-Fernandes, Iryna Yevseyeva, José R. Méndez, Jiaqi Zhao, Florentino Fdez-Riverola, Michael T.M. Emmerich, A spam filtering multi-objective optimization study covering parsimony maximization and three-way classification, Applied Soft Computing, Volume 48, 2016, Pages 111-123, ISSN 1568-4946, https://doi.org/10.1016/j.asoc.2016.06.043.
dc.identifier.doi	10.1016/j.asoc.2016.06.043
dc.identifier.issn	1568-4946
dc.identifier.uri	http://hdl.handle.net/10400.8/12998
dc.language.iso	eng
dc.peerreviewed	yes
dc.publisher	Elsevier BV
dc.relation.hasversion	https://www.sciencedirect.com/science/article/abs/pii/S1568494616303234
dc.relation.ispartof	Applied Soft Computing
dc.rights.uri	http://creativecommons.org/licenses/by-nc-nd/4.0/
dc.subject	Spam filtering
dc.subject	Multi-objective optimization
dc.subject	Parsimony
dc.subject	Three-way classification
dc.subject	Rule-based classifiers
dc.subject	SpamAssassin
dc.title	A spam filtering multi-objective optimization study covering parsimony maximization and three-way classification	eng
dc.type	journal article
dspace.entity.type	Publication
oaire.citation.endPage	123
oaire.citation.startPage	111
oaire.citation.title	Applied Soft Computing
oaire.citation.volume	48
oaire.version	http://purl.org/coar/version/c_970fb48d4fbd8a85
person.familyName	Basto-Fernandes
person.givenName	Vitor
person.identifier.ciencia-id	581C-52BB-AC4E
person.identifier.orcid	0000-0003-4269-5114
person.identifier.rid	N-1891-2016
person.identifier.scopus-author-id	53363129900
relation.isAuthorOfPublication	fb2d3703-9d6a-4c22-bbc4-9ff14c162feb
relation.isAuthorOfPublication.latestForDiscovery	fb2d3703-9d6a-4c22-bbc4-9ff14c162feb