Multi-facet classification of e-mails in a helpdesk scenario

Beckers, Thomas; Frommholz, Ingo; Bonning, Ralf

dc.contributor.author	Beckers, Thomas	en_GB
dc.contributor.author	Frommholz, Ingo	en_GB
dc.contributor.author	Bonning, Ralf	en_GB
dc.date.accessioned	2013-03-22T12:35:49Z
dc.date.available	2013-03-22T12:35:49Z
dc.date.issued	2009
dc.identifier.citation	Beckers, T., Frommholz, I. Bönning, R. (2009) 'Multi-facet Classification of E-Mails in a Helpdesk Scenario,' in Proc. of the GI Information Retrieval Workshop at LWA 2009	en_GB
dc.identifier.uri	http://hdl.handle.net/10547/275694
dc.description.abstract	Helpdesks have to manage a huge amount of support requests which are usually submitted via e-mail. In order to be assigned to experts e ciently, incoming e-mails have to be classi- ed w. r. t. several facets, in particular topic, support type and priority. It is desirable to perform these classi cations automatically. We report on experiments using Support Vector Machines and k-Nearest-Neighbours, respectively, for the given multi-facet classi - cation task. The challenge is to de ne suitable features for each facet. Our results suggest that improvements can be gained for all facets, and they also reveal which features are promising for a particular facet.
dc.language.iso	en	en
dc.publisher	Gesellschaft für Informatik e.V.	en_GB
dc.relation.url	http://www.is.inf.uni-due.de/bib/docs/Beckers_etal_09.html.en	en_GB
dc.rights.uri	http://creativecommons.org/licenses/by-nc-nd/4.0/	*
dc.subject	helpdesks	en_GB
dc.subject	classification	en_GB
dc.subject	Support Vector Machines	en_GB
dc.subject	k-Nearest-Neighbours	en_GB
dc.subject	email	en_GB
dc.subject	facet	en_GB
dc.title	Multi-facet classification of e-mails in a helpdesk scenario	en
dc.type	Conference papers, meetings and proceedings	en
dc.contributor.department	University of Duisburg-Essen, Germany	en_GB
dc.contributor.department	University of Glasgow	en_GB
dc.contributor.department	d.velop AG	en_GB
html.description.abstract	Helpdesks have to manage a huge amount of support requests which are usually submitted via e-mail. In order to be assigned to experts e ciently, incoming e-mails have to be classi- ed w. r. t. several facets, in particular topic, support type and priority. It is desirable to perform these classi cations automatically. We report on experiments using Support Vector Machines and k-Nearest-Neighbours, respectively, for the given multi-facet classi - cation task. The challenge is to de ne suitable features for each facet. Our results suggest that improvements can be gained for all facets, and they also reveal which features are promising for a particular facet.