Show simple item record  

dc.contributor.authorCarmona-Cejudo, José M.
dc.contributor.authorBaena-García, Manuel
dc.contributor.authorCampo-Ávila, José
dc.contributor.authorBifet, Albert
dc.contributor.authorGama, João
dc.contributor.authorMorales-Bueno, Rafael
dc.coverage.spatialConference held at Porto, Portugalen_NZ
dc.date.accessioned2012-12-17T20:15:20Z
dc.date.available2012-12-17T20:15:20Z
dc.date.copyright2011
dc.date.issued2011
dc.identifier.citationCarmona-Cejudo, J. M., Baena-García, M., Campo-Ávila, J., Bifet, A., Gama, J., & Morales-Bueno, R. (2011). Lecture Notes in Computer Science. (D. Hutchison, T. Kanade, J. Kittler, J. M. Kleinberg, F. Mattern, J. C. Mitchell, & J. Hollmén, Eds.) (Vol. 7014, pp. 90-100).en_NZ
dc.identifier.isbn9783642248009
dc.identifier.urihttps://hdl.handle.net/10289/6957
dc.description.abstractReal-time email classification is a challenging task because of its online nature, subject to concept-drift. Identifying spam, where only two labels exist, has received great attention in the literature. We are nevertheless interested in classification involving multiple folders, which is an additional source of complexity. Moreover, neither cross-validation nor other sampling procedures are suitable for data streams evaluation. Therefore, other metrics, like the prequential error, have been proposed. However, the prequential error poses some problems, which can be alleviated by using mechanisms such as fading factors. In this paper we present GNUsmail, an open-source extensible framework for email classification, and focus on its ability to perform online evaluation. GNUsmail’s architecture supports incremental and online learning, and it can be used to compare different online mining methods, using state-of-art evaluation metrics. We show how GNUsmail can be used to compare different algorithms, including a tool for launching replicable experiments.en_NZ
dc.language.isoen
dc.publisherSpringeren_NZ
dc.relation.urihttp://link.springer.com/chapter/10.1007/978-3-642-24800-9_11en_NZ
dc.sourceIDA 2011en_NZ
dc.subjectEmail Classificationen_NZ
dc.subjectOnline Methodsen_NZ
dc.subjectConcept Driften_NZ
dc.subjectText Miningen_NZ
dc.titleOnline evaluation of email streaming classifiers using GNUsmailen_NZ
dc.typeConference Contributionen_NZ
dc.identifier.doi10.1007/978-3-642-24800-9_11en_NZ
dc.relation.isPartOfProc 10th International Symposium on Advances in Intelligent Data Analysis Xen_NZ
pubs.begin-page90en_NZ
pubs.elements-id21516
pubs.end-page100en_NZ
pubs.finish-date2011-10-31en_NZ
pubs.place-of-publicationBerlinen_NZ
pubs.start-date2011-10-29en_NZ
pubs.volumeLNCS 7014en_NZ


Files in this item

FilesSizeFormatView

There are no files associated with this item.

This item appears in the following Collection(s)

Show simple item record