The aim of the task reported in this Deliverable 4.3 was to explore how we could arrive at shared metadata enrichment, by making the most of the large amount of data already gathered in Europeana and the Cloud environment developed in the project. We explored whether we could enrich the data by comparing Europeana data with data from external sources (task 4.3.1). Secondly, we explored whether there was data internally in the large Europeana set that could meaningfully be connected to other data in the set (task 4.3.2). Both approaches would offer better contextualisation of Europeana data for the end user. In Task 4.3.1, ISTI­CNR demonstrated the use of image recognition techniques to explore possible overlap between the datasets of Europeana and the WikiArt data set. As a side effect, it showed that duplicates within the Europeana data set might also surface. The pilot showed how information from an external resource such as WikiArt can potentially be used to enrich the data that is already held in Europeana. A second test phase in February 2016 will increase the Europeana and WikiArt datasets, ensure a more precise selection and focus on paintings held in Europeana, improve matching against WikiArt, and enhance performance.

Europeana Cloud - Deliverable 4.3 - A report and a plan on future directions for improving metadata in the Europeana Cloud

Concordia C;
2016

Abstract

The aim of the task reported in this Deliverable 4.3 was to explore how we could arrive at shared metadata enrichment, by making the most of the large amount of data already gathered in Europeana and the Cloud environment developed in the project. We explored whether we could enrich the data by comparing Europeana data with data from external sources (task 4.3.1). Secondly, we explored whether there was data internally in the large Europeana set that could meaningfully be connected to other data in the set (task 4.3.2). Both approaches would offer better contextualisation of Europeana data for the end user. In Task 4.3.1, ISTI­CNR demonstrated the use of image recognition techniques to explore possible overlap between the datasets of Europeana and the WikiArt data set. As a side effect, it showed that duplicates within the Europeana data set might also surface. The pilot showed how information from an external resource such as WikiArt can potentially be used to enrich the data that is already held in Europeana. A second test phase in February 2016 will increase the Europeana and WikiArt datasets, ensure a more precise selection and focus on paintings held in Europeana, improve matching against WikiArt, and enhance performance.
2016
Istituto di Scienza e Tecnologie dell'Informazione "Alessandro Faedo" - ISTI
Rapporto intermedio di progetto
Digital Library
Metadata enrichment
Europeana
File in questo prodotto:
File Dimensione Formato  
prod_430649-doc_153920.pdf

accesso aperto

Descrizione: Europeana Cloud - Deliverable 4.3
Dimensione 1.68 MB
Formato Adobe PDF
1.68 MB Adobe PDF Visualizza/Apri

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/20.500.14243/408555
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus ND
  • ???jsp.display-item.citation.isi??? ND
social impact