Automated Processing and Exploitation of Heraldic Data from European Archives. – by Torsten Hiltmann and Philipp Schneider

The European Digital Treasures team continues with the presentations of the experts who participated in the workshop “New Digital Exponential Technologies Towards The Generation Of Business Models” on 2nd and 3rd of September, 2021 at the Provincial Historical Archive of Alicante (Spain). 

The second speech on September 3rd was held by Torsten Hiltmann and Philipp Schneider. Torsten Hiltmann is a professor for Digital History at Humboldt-Universität zu Berlin since 2020. His research focuses on the integration of Machine Learning and Semantic Web Technologies into historical studies and on the epistemological change of historical research through the application of digital methods.

Philipp Schneider is a research assistant at the chair of Digital History at Humboldt-Universität zu Berlin since 2020. He works in a project called “Coats of Arms in practice”, where he is responsible for modeling and contextualizing heraldry as a historical source with the help of Semantic Web Technologies.

Abstract. The paper addresses the issue of reusing data from historical archives (and GLAM institutions in general) in data-driven research projects by presenting a catalogue of supporting factors. These factors center around the FAIR principles and how archives and other GLAM institutions can support research by implementing them in their data services. Mainly, historical data should be made accessible through APIs, be describable through its historical context, and to be as interoperable and reusable as possible. These preconditions for using archival data in data-driven historical research are presented by using the example of the research project “Coats of arms in practice”. It aims to study the development and usage of heraldry as a tool of visual communication in the Middle Ages and the Early Modern Period. It employs a data-first approach by integrating data of coats of arms as well as the historical contexts of sources in which they were used into a single Knowledge Graph, built with Semantic Web Technologies. The coats of arms themselves will be described with the help of a specific ontology. Image detection methods based on Machine Learning are used to detect (and describe) coats of arms in image data of historical sources that have not yet been described. This paper focuses on the reuse of archival data from a research perspective. We would like to address the preconditions archival data and GLAM data in general has to meet from the point of view of data-driven research – especially when such research draws on data from multiple institutions. 

You can watch the whole session on YouTube here and read the manuscript paper here!

Written by Torsten Hiltmann, Philipp Schneider & the European Digital Treasures Team.