Welcome to a hands-on introduction to topic modeling with BERTopic, presented by KBLab as part of the national infrastructure Huminfra.
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 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.
Practicalities
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. 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.
Registration to the event is open until the 22nd November.
Read more and register trough Kungliga bibliotekets website.
Foto: Unsplash.