Europeana provides APIs (Application Programming Interfaces) for both end users and content providers, in an effort to enable stakeholders (institutions and private developers) to build their own applications, leading to an increasing number of projects that are built around the Europeana API and are run by various cultural/touristic institutions and companies. However, due to the large volume of digitized cultural artifacts there is not enough qualified human resources available to provide manual indexing This problem affects Europeana, where the search results following a user query are often mixed with partially or totally irrelevant items which are linked in some way with the search input keywords due to incomplete/incorrect or ambiguous metadata. In order to properly address the challenges described above, we propose the use of automated, intelligent techniques that allow the interpretation and classification of digital cultural artifacts and the refinement/ranking of search results. We apply a mixed approach using Web architectures for implementing a user-friendly search engine and a Deep Learning model that performs image classification in order to achieve an improvement in the relevance of the search results from Europeana.
CITATION STYLE
Machidon, O., Stoica, D., & Tavčar, A. (2020). Enhancing the Usability of European Digital Cultural Library Using Web Architectures and Deep Learning. In Springer Proceedings in Business and Economics (pp. 201–207). Springer Science and Business Media B.V. https://doi.org/10.1007/978-3-030-36342-0_16
Mendeley helps you to discover research relevant for your work.