Topic modeling with BERTopic
Welcome to a hands-on introduction to topic modeling with BERTopic, presented by KBLab.
Topic modeling is an exciting option for exploring and finding patterns in large volumes of text data. While this has become an established approach for digital researchers over the past decade, it previously required a level of technical competence that prohibited its uptake among especially humanities scholars.
This has changed with the innovation of BERTopic Länk till annan webbplats., which offers a more accessible means of topic modeling. Taking advantage of the vast processing power of transformer-based language models – i.e. BERT – the new method offers the analytical insights of topic models with just a fraction of the programming efforts.
About the workshop
This workshop offers a hands-on introduction to transformer-based topic modeling with BERTopic. After a brief introduction to the notion of topic models, we offer a step-by-step guide of what is involved in producing such a model, before concluding with a discussion of the process of interpreting the results.
Through practical exposure to the mechanics of modeling, we provide participants with the skills – and curiosity – to consider using this approach in their own research projects. Participants will be able re-use the code script with their own data after the workshop.
Wednesday 6th December, 13.00–15.00.
The workshop will be held online in English via Zoom. We use Swedish OA data, but all instructions are in English. No prior experience of programming is necessary; this is a beginner’s workshop.
The workshop is free of charge and made possible by funding from Huminfra Länk till annan webbplats.. To follow the practical part of the workshop you will need to have a Google account with which you can log into Colab, which is the platform for our interactive teaching material.
How to apply?
Send an e-mail to firstname.lastname@example.org by Friday 24th November.
While open to all, including researchers and Masters students, space will be prioritized for PhD candidates. Places are limited so please get in touch if you are interested in taking part!
KBLab Länk till annan webbplats. is a national infrastructure for digital research at the National Library of Sweden (KB). Beyond supporting large-scale analysis of KB’s collections by digital research projects in the humanities and social science, we use the library’s vast data resources to train and release open-source AI models that are being used by a wide range of actors in the public sector and beyond. You can read more about our development projects within AI and data science on KBLab's blog Länk till annan webbplats..