Meeting the machines half-way: testing LLMs for qualitative coding of values in texts
Which qualitative research tasks can LLMs supplement or replace? What are their strengths and limitations? How can human researchers collaborate with them?
Our research currently focuses on but is not limited to the following research topics.:
- Natural language processing tools for historical newspaper analysis
- Comparative analysis of historical newspaper collections
- Producing semantics data and evaluation datasets from lexical resources
- Injecting knowledge into large language models
- AI Infrastructure for data-driven folkloristics
- Explanation of generative large language models
- Tools for social science analyses of news media in less-resourced languages
Use cases
Advancing Extreme Multi-Label Text Classification for Less-Represented Languages
Dr Nada Lavrač has published a new research article titled “Extreme Multi-Label Text Classification for Less-Represented Languages and Low-Resource Environments: Advances and Lessons Learned” with co-authors. The study addresses a major challenge in contemporary Natural Language Processing...
AR-Q-former: Historical Newspaper Article Separation Based on Multilingual Transformer Structure
A novel multimodal approach for article separation in historical newspapers leverages both textual data and visual information to improve segmentation accuracy.
AI methods for studying media homogenisation
This article briefly explains one case study where media and journalism scholars productively come together with computer science scholars.