From Documents to Data: Digital Technologies in the Study of Notarial Charters

Our contribution presents an ongoing research effort that investigates late medieval notarial charters using advanced computational methods. Drawing from the Monasterium.net archive, we build a curated corpus of 14th–15th-century documents, primarily from Southern Italy, Austria, and Germany. We aim to identify and analyze notarial practices and documentary typologies through text mining, information extraction, and network analysis. A custom annotation scheme is being developed to deploy machine learning and rule-based models tailored to the historical and linguistic complexity of the sources. By extracting named entities and relationships and visualizing them, we explore the social networks and documentary formulas embedded in the charters. The work contributes to the development of digital diplomatics and supports the evolution of Monasterium.net as a platform for computational cultural heritage research.