Workshop on Content Analysis for Digital Humanities (13/06/2025)

This half-day workshop introduces participants to computational content analysis methods, with a focus on historical and literary sources. With the growing availability of digitized texts, thanks to recent advances in OCR and large-scale digitalization projects, researchers increasingly need methods for exploring large corpora that go beyond close reading. Drawing on the concept of Distant Reading (Moretti, 2013), we will explore a range of techniques including document classification, keyword detection, topic modelling, semantic mapping, and the use of transformer-based models such as LLaMA. Example corpora include historical English texts (1500–2000) and the works of Charles Dickens. The format blends theory and hands-on practice. Participants are encouraged to bring their own datasets and research questions, which we may incorporate during the session. Basic knowledge of R or Python is helpful but not required.

Note: Participants are invited to send their datasets and research questions at least one week before the workshop.

🗓 Date/Time Friday, June 13, 2025 09:00 – 13:30

📍 Location: University of Zurich KOL-H-317, 3rd floor, Rämistrasse 71 8006 Zürich

👥 Organizer: DSI Community Digital Humanities in collaboration with Prof. Dr. Gerold Schneider

🔗 Registration: Register here