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
On using active learning and self-training when mining performance discussions on stack overflow
RISE., Swedish ICT, SICS, Security Lab.ORCID-id: 0000-0001-7879-4371
Lund University, Sweden.
Lund University, Sweden.
Lund University, Sweden.
2017 (engelsk)Inngår i: EASE'17 Proceedings of the 21st International Conference on Evaluation and Assessment in Software Engineering. ACM International Conference Proceeding Series, 2017, s. 308-313Konferansepaper, Publicerat paper (Fagfellevurdert)
Abstract [en]

Abundant data is the key to successful machine learning. However, supervised learning requires annotated data that are often hard to obtain. In a classification task with limited resources, Active Learning (AL) promises to guide annotators to examples that bring the most value for a classifier. AL can be successfully combined with self-training, i.e., extending a training set with the unlabelled examples for which a classifier is the most certain. We report our experiences on using AL in a systematic manner to train an SVM classifier for Stack Overflow posts discussing performance of software components. We show that the training examples deemed as the most valuable to the classifier are also the most difficult for humans to annotate. Despite carefully evolved annotation criteria, we report low inter-rater agreement, but we also propose mitigation strategies. Finally, based on one annotator's work, we show that self-training can improve the classification accuracy. We conclude the paper by discussing implication for future text miners aspiring to use AL and self-training.

sted, utgiver, år, opplag, sider
2017. s. 308-313
Emneord [en]
Active learning, Classification, Human annotation, Self-training, Text mining, Artificial intelligence, Classification (of information), Data mining, Software engineering, Text processing, Classification accuracy, Classification tasks, Human annotations, Inter-rater agreements, Mitigation strategy, Self training, Education
HSV kategori
Identifikatorer
URN: urn:nbn:se:ri:diva-30875DOI: 10.1145/3084226.3084273Scopus ID: 2-s2.0-85025467713ISBN: 9781450348041 (tryckt)OAI: oai:DiVA.org:ri-30875DiVA, id: diva2:1139371
Konferanse
21st International Conference on Evaluation and Assessment in Software Engineering, EASE 2017, 15 June 2017 through 16 June 2017
Prosjekter
ORIONTilgjengelig fra: 2017-09-07 Laget: 2017-09-07 Sist oppdatert: 2018-07-19bibliografisk kontrollert

Open Access i DiVA

Fulltekst mangler i DiVA

Andre lenker

Forlagets fulltekstScopus

Personposter BETA

Borg, Markus

Søk i DiVA

Av forfatter/redaktør
Borg, Markus
Av organisasjonen

Søk utenfor DiVA

GoogleGoogle Scholar

doi
isbn
urn-nbn

Altmetric

doi
isbn
urn-nbn
Totalt: 31 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
v. 2.35.8