LLMs in Social Science

Today, We are joined by Petter Törnberg, an Assistant Professor in Computational Social Science at the University of Amsterdam and a Senior Researcher at the University of Neuchatel. His research is centered on the intersection of computational methods and their applications in social sciences. He joins us to discuss findings from his research papers, ChatGPT-4 Outperforms Experts and Crowd Workers in Annotating Political Twitter Messages with Zero-Shot Learning, and How to use LLMs for Text Analysis.

Petter started by discussing the history of computational social science, from neoclassical economics to heterodox economics to now discovering theories from data and models. Delving into his research, he shared his motivation. Petter wanted to see if ChatGPT can annotate political tweets better than experts. He revealed the shocking results.

Petter gave his thoughts on the black-box nature of LLMs. He also discussed the use of LLMs to identify populism in texts. He also discussed prompt engineering strategies that can improve the output of LLMs.

Petter discussed how LLMs can be used in other social science fields. He advised social science students on how to maximize LLMs in their work. Follow Petter on Twitter/X @pettertornberg. Learn more about Petter’s work on his Google Scholar page.

Resources

Jupyter Notebook: How to use LLMs for Text Analysis.