[This post was written by Esra Atesçelik. It describes her MSc. project supervised by Antoine Isaac and myself]
The digital libraries and aggregators such as Europeana provide access to millions of Cultural Heritage Objects (CHOs). Europeana is one of the libraries which does not maintain collection-level metadata. Europeana can cluster the objects that have common information with each other. It can use collection-level information to organize results and help users.
In this project we want to show how we can cluster the objects from Europeana datasets. We also aim at finding the best way of clustering on Europeana metadata and the best parametric setting for clustering. We apply various clustering methods on Europeana metadata and aim at proposing a clustering technique that is most appropriate to group Europeana CHOs. In the experiments we evaluated the cluster results manually, on qualitative and quantitative level.
The results of experiments showed that it is difficult to define the best parametric setting and best clustering method only based on a number of experiments. However, we have shown a way to cluster Europeana objects which may be useful for Europeana.