.png)
Course description
Qualitative research often involves time-consuming analysis of textual material, making it difficult to investigate large collections of documents, interviews, or other texts. Recent developments in artificial intelligence, particularly large language models (LLMs), offer new opportunities to overcome these limitations, allowing researchers to analyse substantially larger datasets while retaining many of the interpretive strengths of qualitative research.
This hands-on workshop introduces participants to a practical methodology for AI-assisted qualitative text classification. Participants will work with sample texts to develop their own coding guidelines, apply them using AI, and evaluate and refine the results. The workshop will also explore how this process can be scaled to thousands of texts, alongside important considerations of reliability, validity, and research ethics.
The workshop is designed for qualitative researchers, regardless of their technical background. No programming experience is required.
Target audience
The workshop is primarily designed for master's students, PhD candidates, and researchers who use qualitative methods and wish to analyse larger collections of textual data more efficiently.
It is particularly relevant to researchers in the humanities and social sciences, but is open to participants from all scientific disciplines working with qualitative textual data.
Learning outcomes
- Understand the opportunities and limitations of using large language models (LLMs) to scale qualitative text analysis.
- Develop clear and systematic coding guidelines suitable for AI-assisted classification.
- Evaluate AI-generated classifications, identify inconsistencies, and iteratively refine coding guidelines to improve reliability.
- Understand how AI-assisted classification can be scaled to larger text corpora, including the role of automation and APIs.
- Recognize key methodological considerations, including validity, reproducibility, research ethics, and data protection.
Prerequisites
- Basic familiarity with qualitative research methods, particularly working with textual data, is recommended. Previous experience with qualitative coding is helpful but not required.
- No prior knowledge of artificial intelligence, programming, or computational text analysis is necessary, but helpful.
- Entry level: beginner
Required materials
- Participants should bring:
- A laptop with internet access.
- Access to GPT UiO or another browser-based AI model.
- Optionally, a sample of textual data from their own research that they would like to work with.
Lunch
- There will be a complementary buffet-lunch at 12:00-13:00 from the Sverdrups spiseri (Georg Sverdrups Hus, 2nd floor).
- After you get your lunch, join us at Store møterom where we have reserved seats for #DSDays2027 participants.
Number of participants
30
Contact
If you have any questions regarding this course, or anything else about the DSDays 2027 event, please contact us per email: digitalscholarship@ub.uio.no