A hands-on research event at the Bibliothèque nationale de France (BnF)
We are pleased to invite researchers to the Impresso@BnF Datathon, a three-day hands-on research event co-organised by the Impresso project and the Bibliothèque nationale de France, hosted at the BnF in Paris on 28–30 October 2026.
About the event
This datathon brings together an international group of researchers curious about the computational analysis of historical media collections across languages and modalities and offers them tools, data, models, and expert support. The event will rely on English as a shared language.
Participants will work in small teams on self-defined research questions, drawing on BnF's collections and Impresso resources: a multilingual media corpus, derived datasets, NLP and vision models, and the Impresso Datalab. The Impresso team will be present throughout to guide, support, and collaborate.
Programme overview
The event unfolds over three days at the BnF:
- Day 1 (afternoon): Introduction to the Impresso Web App and Datalab through presentations and live demonstrations; group formation around shared research interests
- Days 2 & 3: Hands-on research work, with guided sessions on embeddings and data-driven analysis, team project time, and a closing round of group presentations and collective reflection
Sessions are designed with flexibility in mind: participants can engage with specific components according to their experience level and research focus. Dedicated exchange "stations" allow for direct, informal conversation with organisers at any point during the event.
Participation is limited to a maximum of 30 people to ensure a productive, discussion-oriented environment.
During registration, you will be asked to briefly describe your research interests. These responses will directly shape the event agenda and the selection of case studies, so we encourage you to be specific.
What Impresso offers
At the heart of this datathon is the Impresso Datalab, a research environment for the computational analysis of digitised historical press, combining an exploration interface with a computational workspace. Participants will have access to:
- The Impresso Web App: an interface for exploring and querying a semantically enriched multilingual corpus of digitised newspapers and radio broadcasts
- The Impresso Datalab: a computational environment for data-driven analysis, accompanied by derived datasets, NLP models (available on Hugging Face), and multimodal embeddings enabling cross-lingual text search, image-text linking, and semantic analysis across heterogeneous archival collections
- Dedicated training materials and case study Jupyter notebooks to support participants across a range of technical backgrounds
Whether your sources are in French, German, English, or another European language, and whether you work with text, images, or both, the Datalab provides tools to connect, annotate, and query historical collections at scale.
Registration
This datathon is well suited for:
- Historians and media scholars working with digitised press archives
- Digital humanities researchers interested in computational methods for cultural heritage
- Information scientists and librarians exploring AI-powered access to archival collections
- Advanced students and early-career researchers with an interest in historical data analysis
👉Register here: https://forms.gle/hQpNBrtMRVhKuMCp9
Prior programming or data analysis experience is helpful but not required. Ready-to-use case study notebooks will be provided to lower the barrier to entry, and the Impresso team will offer hands-on support throughout.
We look forward to welcoming you to Paris for what we hope will be a productive and enjoyable few days.
For questions, please contact info@impresso-project.ch