Predicting Quality of Crowdsourced Annotations Using Graph Kernels

None, None; None, None; None, None; None, None; None, None

Predicting Quality of Crowdsourced Annotations Using Graph Kernels

Conference Paper (2015)

Author(s)

Archana Nottamkandath (Vrije Universiteit Amsterdam)

Jasper Oosterman (TU Delft - Electrical Engineering, Mathematics and Computer Science)

Davide Ceolin (Vrije Universiteit Amsterdam)

Gerben Klaas Dirk de Vries (Universiteit van Amsterdam)

Wan Fokkink (Vrije Universiteit Amsterdam)

Research Group

Web Information Systems

DOI related publication

https://doi.org/10.1007/978-3-319-18491-3_10 Final published version

To reference this document use

https://resolver.tudelft.nl/uuid:fff17003-2ce8-4045-8227-b96cb2a16afe

More Info

expand_more

Publication Year

2015

Language

English

Research Group

Web Information Systems

Volume number

454

Pages (from-to)

134-148

Publisher

Springer

ISBN (print)

978-3-319-18490-6

Downloads counter

151

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.