< Back to previous page


STUDIUM.AI – Datafying the ‘webs of knowledge’ around the Old University of Leuven

STUDIUM.AI will develop a research infrastructure to
examine the ‘webs of knowledge’ around the Old University
in Leuven (1425-1797) from a data- and AI-driven
perspective. As a first objective, STUDIUM.AI will allow 8
teams in 4 faculties to collaborate within the same
sustainable LOD-environment on data of students, scholars,
texts, ideas and images in premodern Leuven, a major
knowledge hub at Europe's crossroads. By its
interdisciplinary scope, the RI overcomes the
methodological divide between our current texts-, personsand
image-based datasets. Secondly, an HTR-model will be
developed to generate full-text from handwritten
manuscripts containing lecture notes of Leuven students.
The resulting corpora will be mined and linked through NLPprocesses
of Named Entity Recognition (NER) and Named
Entity Linking (NEL). Thirdly, as a result, STUDIUM.AI
envisages to create a data pool of about 166,000 records,
which is exponentially larger than the current 8 datasets
stemming from projects or heritage initiatives (between
400 and 10,000 entries). These ‘big data’ will allow to
integrate recent AI-driven algorithms in network analysis to
detect ‘clusters’ which remain invisible within individual
disciplines and projects, or ‘hidden’ because of power,
gender or migration. Hence, STUDIUM.AI offers a
methodological reflection on how DH- and AI-methods can
help to rethink the transmission of knowledge in past and
present within an intersectional and inclusive analysis.
Non-confidential summary in layman's terms
Applicant: Violet Soen | Application number:

Date:1 May 2022 →  Today
Keywords:research infrastructure, Old University in Leuven (1425-1797), data pool, intersectional and inclusive analysis
Disciplines:Data mining