Predicting Quality of Crowdsourced Annotations Using Graph Kernels - Trust Management IX Access content directly
Conference Papers Year : 2015

Predicting Quality of Crowdsourced Annotations Using Graph Kernels

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.
Fichier principal
Vignette du fichier
337890_1_En_10_Chapter.pdf (929.88 Ko) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

hal-01416219 , version 1 (14-12-2016)

Licence

Attribution

Identifiers

Cite

Archana Nottamkandath, Jasper Oosterman, Davide Ceolin, Gerben De Vries, Wan Fokkink. Predicting Quality of Crowdsourced Annotations Using Graph Kernels. 9th IFIP International Conference on Trust Management (TM), May 2015, Hamburg, Germany. pp.134-148, ⟨10.1007/978-3-319-18491-3_10⟩. ⟨hal-01416219⟩
64 View
84 Download

Altmetric

Share

Gmail Facebook X LinkedIn More