Endre søk
RefereraExporteraLink to record
Permanent link

Direct link
Referera
Referensformat
  • apa
  • harvard1
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Annet format
Fler format
Språk
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Annet språk
Fler språk
Utmatningsformat
  • html
  • text
  • asciidoc
  • rtf
Using conformal prediction for multi-label document classification in e-Mail support systems
Blekinge Tekniska Högskola, Fakulteten för datavetenskaper, Institutionen för datavetenskap.ORCID-id: 0000-0002-8929-7220
Blekinge Tekniska Högskola, Fakulteten för datavetenskaper, Institutionen för datavetenskap.ORCID-id: 0000-0002-9316-4842
Telenor Sverige AB, SWE.
2019 (engelsk)Inngår i: Lect. Notes Comput. Sci., Springer Verlag , 2019, Vol. 11536, s. 308-322Konferansepaper, Publicerat paper (Fagfellevurdert)
Abstract [en]

For any corporation the interaction with its customers is an important business process. This is especially the case for resolving various business-related issues that customers encounter. Classifying the type of such customer service e-mails to provide improved customer service is thus important. The classification of e-mails makes it possible to direct them to the most suitable handler within customer service. We have investigated the following two aspects of customer e-mail classification within a large Swedish corporation. First, whether a multi-label classifier can be introduced that performs similarly to an already existing multi-class classifier. Second, whether conformal prediction can be used to quantify the certainty of the predictions without loss in classification performance. Experiments were used to investigate these aspects using several evaluation metrics. The results show that for most evaluation metrics, there is no significant difference between multi-class and multi-label classifiers, except for Hamming loss where the multi-label approach performed with a lower loss. Further, the use of conformal prediction did not introduce any significant difference in classification performance for neither the multi-class nor the multi-label approach. As such, the results indicate that conformal prediction is a useful addition that quantifies the certainty of predictions without negative effects on the classification performance, which in turn allows detection of statistically significant predictions. © Springer Nature Switzerland AG 2019.

sted, utgiver, år, opplag, sider
Springer Verlag , 2019. Vol. 11536, s. 308-322
Serie
Lecture Notes in Computer Science ; 11536
Emneord [en]
Conformal prediction, Customer support e-mail, Multi-label classification, Electronic mail, Forecasting, Information retrieval systems, Intelligent systems, Sales, Classification performance, Conformal predictions, Customer support, Document Classification, Email classification, Evaluation metrics, Multi label classification, Multi-class classifier, Classification (of information)
HSV kategori
Identifikatorer
URN: urn:nbn:se:bth-18592DOI: 10.1007/978-3-030-22999-3_28Scopus ID: 2-s2.0-85068624865ISBN: 9783030229986 (tryckt)OAI: oai:DiVA.org:bth-18592DiVA, id: diva2:1349335
Konferanse
International Conference on Computational Science, ICCS, Faro, Algarve, 9 July 2019 through 11 July 2019
Tilgjengelig fra: 2019-09-09 Laget: 2019-09-09 Sist oppdatert: 2019-09-20bibliografisk kontrollert

Open Access i DiVA

Fulltekst mangler i DiVA

Andre lenker

Forlagets fulltekstScopus

Personposter BETA

Borg, AntonBoldt, Martin

Søk i DiVA

Av forfatter/redaktør
Borg, AntonBoldt, Martin
Av organisasjonen

Søk utenfor DiVA

GoogleGoogle Scholar

doi
isbn
urn-nbn

Altmetric

doi
isbn
urn-nbn
Totalt: 41 treff
RefereraExporteraLink to record
Permanent link

Direct link
Referera
Referensformat
  • apa
  • harvard1
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Annet format
Fler format
Språk
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Annet språk
Fler språk
Utmatningsformat
  • html
  • text
  • asciidoc
  • rtf