Predicting Quality of Crowdsourced Annotations using Graph Kernels

Archana Nottamkandath, Jasper Oosterman, Gerben Klaas Dirk de Vries, Davide Ceolin, Wan Fokkink

Research output: Chapter in Book / Report / Conference proceedingConference contributionAcademicpeer-review

Abstract

Annotations obtained by Cultural Heritage institutions from the crowd need to be automatically assessed for their quality. Machine learning using graph kernels is an effective technique to use structural information in datasets to make predictions. We employ the Weisfeiler- Lehman graph kernel for RDF to make predictions about the quality of crowdsourced annotations in Steve.museum dataset, which is modelled and enriched as RDF. Our results indicate that we could predict quality of crowdsourced annotations with an accuracy of 75%. We also employ the kernel to understand which features from the RDF graph are relevant to make predictions about different categories of quality.
Original languageEnglish
Title of host publicationTrust Management IX - 9th IFIP Working Group 11.11 International Conference on Trust Management, IFIPTM 2015, Proceedings
EditorsY. Murayama, T. Dimitrakos, C. D. Jensen, S. Marsh
PublisherSpringer New York
Pages134-148
Number of pages15
Volume454
ISBN (Print)9783319184906
DOIs
Publication statusPublished - 2015
Event9th IFIP Working Group 11.11 International Conference on Trust Management, IFIPTM 2015 - Hamburg, Germany
Duration: 26 May 201528 May 2015

Publication series

NameIFIP Advances in Information and Communication Technology
Volume454
ISSN (Print)1868-4238

Conference

Conference9th IFIP Working Group 11.11 International Conference on Trust Management, IFIPTM 2015
CountryGermany
CityHamburg
Period26/05/1528/05/15

Keywords

  • Crowdsourcing
  • Machine learning
  • RDF graph Kernels
  • Trust

Fingerprint Dive into the research topics of 'Predicting Quality of Crowdsourced Annotations using Graph Kernels'. Together they form a unique fingerprint.

Cite this