Universiteit Leiden

nl en

Leiden University Centre for Digital Humanities

Nicole van Os

Coordinator of studies


Text mining, OCR of handwritten texts in multiple languages

Current Projects

Using transkribus (transkribus.eu) we are at the moment trying to OCR approximately 550 letters written in a mixture of multiple languages between 1954 - 1974 by a teacher of mathematics of living in Istanbul as a single, Christian woman with a foreign nationality. Once OCR'ed we hope to be able to use this corpus for further linguistic and social historical research using adequate tools (data mining, corpuslinguistics).


Nicole van Os is a researcher of Ottoman and Turkish women's history. Until now, she has had no experience in digital humanities, but she hopes to explore the possibilities available to apply data mining for social historical research in multilingual, handwritten texts.

This website uses cookies. More information