Semantic Technologies for Digital Humanities

March 29, 2019 by Victor de Boer

This year's SEMANTiCS conference features a special sub-topic called Digital Humanities and Cultural Heritage. Through this call, we invite research progress, research challenges but also case studies and industry submissions in these two related domains.

With increased digitization efforts, many cultural heritage datasets are being published online. National and European efforts such as Europeana have led to digitization of heritage objects and publishing objects and metadata online, usually under Open licenses. Information about paintings, library objects, archival material, audio-visual heritage and much more is appearing online at an astonishing rate.

Recently, institutions have started publishing their collections as linked data. Examples include Rijksmuseum Amsterdam, The German National Library or the many vocabularies and datasets published by the Getty institute

Many museums, libraries and (audiovisual) archives publish metadata as Linked Open Data

Discuss Digital Humanities and Culutral Heritage with Victor. Register for SEMANTiCS 2019!

With more and more of this very heterogeneous (meta)data being published online, questions about interoperability arise. As end-users, we would like to be able to explore the relations between a documentary film about Pablo Picasso, his paintings in Paris museums and archival documentation about his life. Knowledge graphs can play an important role here, where explicit semantics are used to express meaning for object metadata and semantic links between datasets integrates these datasets. Shared vocabularies such as those published by Getty can be used as stepping stones to link objects from different collections and data models such as the Europeana Data Model, Dublin Core or CIDOC-CRM can be used to structure metadata and define shared semantics.

One specific use for such semantically interlinked heritage data is that of Digital Humanities. Digital Humanities is an emerging field bringing together researchers and practitioners from the domains of computer science, cultural heritage, humanities and social science. Through the integration of previously unconnected datasets, new types of analyses and research questions become possible.

Examples of Digital Humanities projects that involve semantic technologies are those by Aalto university in Finland, the Linked Jazz project or the "Audio-Visual Rhetorics of Affect" research initiative working on the semantic annotation of audio-visual data.

The DIVE project, to which I personally contributed, brings together heterogeneous heritage datasets and make this knowledge graph explorable through an exploratory interface that matches humanities scholars' needs and research practice.

Example of a heterogeneous cultural heritage knowledge graph linking video material, to photographs, to newspaper articles to museum objects through shared vocabularies and authority files (DIVE project)

These examples show how semantic technologies play a crucial role in addressing new and existing research questions of humanities scholars. On the other hand, the heritage and humanities data present new and interesting challenges to those semantic technologies. These challenges include (but are definitely not limited to) questions about data provenance, how to deal with user annotations and integration of heterogeneous datasets.

For SEMANTiCS2019 we call on the community to not only identify new research challenges or present solutions to these challenges but also report on specific cases, success stories and lessons learned.

Do you want to contribute to this topic? Read the Call for Papers!

About the Author

SEMANTiCS Digital Humanities chair Victor de Boer is an assistant professor at the User-Centric Data Science group at the Computer Science department of the Vrije Universiteit Amsterdam (VU). Furthermore, Victor is a senior research fellow at Netherlands Institute for Sound and Vision. He combines (Semantic) Web technologies with Human-Computer Interaction, Knowledge Representation and Information Extraction in his research to tackle challenges in various domains. These include Cultural Heritage, Digital Humanities and ICT for Development (ICT4D).

http://victordeboer.com

About SEMANTiCS

The annual SEMANTiCS conference is the meeting place for professionals who make semantic computing work, and understand its benefits and know its limitations. Every year, SEMANTiCS attracts information managers, IT-architects, software engineers, and researchers, from organisations ranging from NPOs, universities, public administrations to the largest companies in the world. http://www.semantics.cc