Using Semantic Relations for Content-based Recommender Systems in Cultural heritage

Y. Wang, N. Stash, L.M. Aroyo, L. Hollink, A.Th. Schreiber

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

Abstract

Metadata vocabularies provide various semantic relationsbetween concepts. For content-based recommender systems, these rela-tions enable a wide range of concepts to be recommended. However, notall semantically related concepts are interesting for end users. In this pa-per, we identified a number of semantic relations, which are within onevocabulary (e.g. a concept has a broader/narrower concept) and acrossmultiple vocabularies (e.g. an artist is associated to an art style). Ourgoal is to investigate which semantic relations are useful for recommenda-tions of art concepts and to look at the combined use of artwork featuresand semantic relations in sequence. These sequences of ratings allow usto derive some navigation patterns from users, which might enhance theaccuracy of recommendations and be reused for other recommender sys-tems in similar domains. We tested the CHIP demonstrator, called theArt Recommender with end users by recommending both semantically-related concepts and artworks features (e.g.creator, material, subject).
Original languageEnglish
Title of host publicationWOP 2009 - Workshop on Ontology Patterns
Subtitle of host publicationProceedings of the Workshop on Ontology Patterns (WOP 2009), collocated with the 8th International Semantic Web Conference (ISWC-2009), Washington D.C., USA, 25 October, 2009
EditorsEva Blomqvist, Kurt Sandkuhl, Francois Scharffe, Vojtec Svatek
Place of PublicationChantilly
PublisherCEUR-WS
Chapter2
Pages16-28
Number of pages13
Publication statusPublished - 2009
EventWOP 2009 - Workshop on Ontology Patterns - Washington, D.C.
Duration: 25 Oct 200925 Dec 2009

Publication series

NameCEUR Workshop Proceedings
PublisherCEUR Workshop Proceedings
Volume516
ISSN (Print)1613-0073

Conference

ConferenceWOP 2009 - Workshop on Ontology Patterns
Abbreviated titleWOP 2009
CityWashington, D.C.
Period25/10/0925/12/09

Fingerprint Dive into the research topics of 'Using Semantic Relations for Content-based Recommender Systems in Cultural heritage'. Together they form a unique fingerprint.

Cite this