The many faces of GESIS
Vita
Leah von der Heyde is a computational social scientist and survey methodologist. Her research focuses on the potential and pitfalls of new data sources, such as large language models, for improving the measurement and representation of public opinion. Substantively, she is particularly interested in political attitudes and voting behavior.
Leah received her PhD in Social Data Science and Research Methodology from the University of Mannheim. She has a background in political science from LMU Munich, the University of Mannheim, and Georgetown University. Previously, Leah was part of the Social Data Science and AI Lab at LMU Munich, worked for the European Social Survey at GESIS - Leibniz Institute for the Social Sciences, the European Parliamentary Research Service, and several market and public opinion research institutes in Germany and Sweden. At GESIS, she is part of KODAQS, researching and educating social scientists on AI applications in survey research and their implications for data quality.
Publications
Journal article
von der Heyde, Leah, Anna-Carolina Haensch, Bernd Weiß, and Jessica Daikeler. 2025. "Using Large Language Models for Coding German Open-Ended Survey Responses on Survey Motivation." Survey Research Methods 19 (4): 355-370. doi: https://doi.org/10.18148/SRM/2025.V19I4.8568.
von der Heyde, Leah, Anna‐Carolina Haensch, Alexander Wenz, and Bolei Ma. 2025. "Vox Populi, Vox AI? Using Large Language Models to Estimate German Vote Choice." Social Science Computer Review online first: . doi: https://doi.org/10.1177/08944393251337014.
von der Heyde, Leah, Anna-Carolina Haensch, Alexander Wenz, and Bolei Ma. 2024. "United in Diversity? Contextual Biases in LLM-Based Predictions of the 2024 European Parliament Elections." arXiv: 2409.09045. doi: https://doi.org/10.48550/ARXIV.2409.09045.
Chapter in an edited book
Buskirk, Trent D, Florian Keusch, Leah von der Heyde, and Adam Eck. 2025. "More Parameters Than Populations: A Systematic Review of Large Language Models in Survey Research." In First Workshop on Bridging NLP and Public Opinion Research, https://openreview.net/forum?id=0Hxhwa56Yg.
von der Heyde, Leah. 2025. "Who Counts? The Potentials and Pitfalls of Using LLMs in Survey Research." In First Workshop on Bridging NLP and Public Opinion Research, https://openreview.net/forum?id=ww2KqnPLdK.
Presentation at a conference
Gerdon, Frederic, Leah von der Heyde, and Frauke Kreuter. 2023. "Using survey experiments to longitudinally study privacy as contextual integrity." European Survey Research Association Conference 2023, Milan, 2023-07-21.