The ERC Consolidator project ‘Sharing Knowledge in Learned and Literary Networks – The Republic of Letters as a Pan-European Knowledge Society’ (SKILLNET), under the direction of Dr Dirk van Miert, conducts research into the ideal of sharing knowledge within early modern scholarly networks in Europe by applying social network analysis and text mining techniques to the metadata and full-text data of large quantities of manuscript and printed letters from the period 1500-1800.
Introductory video on Crowdsourcing project
YouTube channel ERC_SKILLNET
LetterSampo is a Linked Open Data (LOD) model for aggregating, publishing, and using epistolary data in Digital Humanities on the Semantic Web. Based on the “Sampo Model”, LetterSampo contains a LOD service and a semantic portal on top of it (SPARQL endpoint) for searching and exploring linked data and data analysis. Demonstrators have been implemented based on the databases of ePistolarium (the Netherlands) and correspSearch (Germany).
Video on using LetterSampo
Sampo model and semantic portals in use
Network analyses are being made on top of the LetterSampo LOD service on ePistolarium data and correspSearch data. The goal is to analyse and compare historical epistolary networks with modern mobile and email communication networks from network analytic points of view.
A new 4-year project funded by the Academy of Finland (2021–2025) is starting focusing on 19th century Finnish correspondences. The LetterSampo model above will be used and developed further here. The consortium members are the Finnish Literature Society (lead), University of Helsinki (HELDIG centre for Digital Humanities), and Aalto University.
The ‘epistolarITA’ project is divided into two principle axes: critical editions of Italian letters, and stylometric and semantic analysis of epistolary texts. A database has been launched, through which users can access the edition of some 500 letters written in Italian between the 15th and 17th centuries and sent from the former Low Countries. At the same time, users can also perform statistical analyses on a large epistolary corpus of letters edited in the framework of international projects. The ‘epistolarITA’ algorithm uses techniques such as TF-IDF, fastText, and Named-Entity Recognition to help users to discover new connections, explore new avenues of research, and find new interpretations in the network of the Republic of letters.