5 papers
Hybrid Panels: Toward Human-AI Collaboration in Survey Research
Julia Romberg, Tobias Gummer, Gabriella Lapesa +2
Large-scale population surveys are essential for generating robust social and scientific insights, yet they face significant challenges, including declining response rates, increas…
German General Social Survey Personas: A Survey-Derived Persona Prompt Collection for Population-Aligned LLM Studies
Jens Rupprecht, Leon Fröhling, Claudia Wagner +1
The use of Large Language Models (LLMs) for simulating human perspectives via persona prompting is gaining traction in computational social science. However, well-curated, empirica…
From Emotion to Expression: Theoretical Foundations and Resources for Fear Speech
Vigneshwaran Shankaran, Gabriella Lapesa, Claudia Wagner
Few forces rival fear in their ability to mobilize societies, distort communication, and reshape collective behavior. In computational linguistics, fear is primarily studied as an…
Facts are Harder Than Opinions -- A Multilingual, Comparative Analysis of LLM-Based Fact-Checking Reliability
Lorraine Saju, Arnim Bleier, Jana Lasser +1
The proliferation of misinformation necessitates scalable, automated fact-checking solutions. Yet, current benchmarks often overlook multilingual and topical diversity. This paper…
Learning from Convenience Samples: A Case Study on Fine-Tuning LLMs for Survey Non-response in the German Longitudinal Election Study
Tobias Holtdirk, Dennis Assenmacher, Arnim Bleier +1
Survey researchers face two key challenges: the rising costs of probability samples and missing data (e.g., non-response or attrition), which can undermine inference and increase t…