Medieval Data Mining
IMC 2013: The introduction to data mining in the process of working with medieval charters were one of the very interesting topics at IMC 2013…
Charters record legal transactions of property of all kinds: houses, workshops, fields and meadows and describe the people who lived there. Long before records such as censuses or birth registers existed charters were and still are the major resource for researching people, for tracing changes in communities over time and for finding ancestors.
The ChartEx Project is developing new ways of exploring the full text content of digital historical records. The project wishes to demonstrate its approach using medieval charters, which survive sporadically from very early on and in abundance from the 12th to the 16th centuries. They are one of the richest sources for studying the lives of people in the past.
According to their website the new ChartEx tools will use a combination of Natural Language Processing (NLP) and Data Mining to extract information about places, people and events in their lives from the charters automatically and find new relationships between these entities. However, the aim of the project is also to build an interactive “virtual workbench” that will allow historians, archivists and others interested in charters to explore the information extracted and add further information and comments.
At the IMC 2013 several large digitisation projects were presented. Amongst these were the ChartEx one of the more promising, since its aim is not so much to establish a new (competing) database but in developing tools, which afterwards can be used in other similar projects.
Present at the session was Rachel Stone who is currently working with Alice Rio, Janet Nelson and others on the AHRC-funded project: The making of Charlemagne’s Europe, 768 -814. This project aims to mark up the more than 4500 documents surviving from this period in order to make it available for scholars trying to get a better overview of the general structure and patterns of Carolingian political forms of organisation, their economic, social and religious foundations and the archival strategies implemented by the scribes and other actors. (This project was presented at a dedicated roundtable in an evening session, where yet another project – the “Nomen et Gens” was also introduced.)
Already she has written a special report of the ChartEx project, which sums it all up in a highly recommendable form (accessible at her blog – Magistra et Mater). As several in the audience, she was also captivated by the possibilities of using data-mining in the process of evaluating the statistical probabilities of the identification of identical persons and places in different charters, hence making more accurate identifications possible for the researcher.