References

• 1952Rank Analysis of Incomplete Block Designs: I. The Method of Paired Comparisons2,408 cited
• 2014Structural Topic Models for Open‐Ended Survey Responses1,967 cited
• 2023ChatGPT outperforms crowd workers for text-annotation tasks1,338 cited
• 1970On Extending the Bradley-Terry Model to Accommodate Ties in Paired Comparison Experiments260 cited
• 2024Large language models as a substitute for human experts in annotating political text117 cited
• 2017Measuring and Explaining Political Sophistication Through Textual Complexity106 cited
• 2023Narratives About the Macroeconomy100 cited
• 2022Do AIs know what the most important issue is? Using language models to code open-text social survey responses at scale96 cited
• 2025Positioning Political Texts with Large Language Models by Asking and Averaging61 cited
• 2025How to train your stochastic parrot: large language models for political texts51 cited
• 2017A Pairwise Comparison Framework for Fast, Flexible, and Reliable Human Coding of Political Texts49 cited
• 2024Measuring What is Top of Mind45 cited
• 2025LLMs outperform outsourced human coders on complex textual analysis18 cited
• 2025Mapping (A)Ideology: A Taxonomy of European Parties Using Generative LLMs as Zero-Shot Learners13 cited