Skip to content

Workshop on content analysis – April 12th 2024; 9:00 – 17:00

Workshop on content analysis – April 12th 2024; 9:00 – 17:00 Article Image

18. March 2024

In the «Workshop on content analysis - Best practices, challenges and opportunities in (automatic) content analysis for social science research: triangulating AI and other approaches to cover ethical topics» participants will learn how to triangulate main approaches and strategies for studying social science related concepts in text collections with (automated) content analysis methods, including large language models. It takes place on the 12th of April form 9a.m. - 5p.m. at the Digital Society Initiative, Rämistrasse 69, 8001 Zurich. Registration below.

Challenges and opportunities of (automatic) content analysis will be discussed and datasets from social media, news media and expert communication are selected to highlight ethical questions while addressing topics of interest for communication, political, linguistic and social sciences (including algorithms, religion, health and ethics).

Against this background, the workshop highlights methods of distant reading and how, due to recent advances, also close reading is increasingly possible automatically. The focus will be on ethical questions and include large language models. The workshop will also pay particular attention to validation and robustness check strategies (e.g., integration of and correlation with external (survey) data, event and manual validations, blackbox models), while highlighting the usefulness of a «human-in-the-loop» component.

The workshop will be held by Prof. Dr. Gerold Schneider and Dr. Maud Reveilhac.


Morning supervised methods – e.g. keyword detection (e.g., using Tf-Idf), text classification (for emotion, sentiment, and policy fields), and rule-based stance detection – and unsupervised methods – topic modelling (e.g., LDA, BERTopic and STM) and semantic analyses. (e.g., distributional semantics and semantic maps).
Afternoon large language models – including BERT and ChatGPT applications – and case studies triangulating the presented methods.

The workshop will include hands-on exercises with R and Python. Participants need basic knowledge of R to follow the workshop. Data and codes will be provided in a dedicated GitLab repository, as well as presentation slides and useful theoretical resources.

Please register here.