LLM Analysis of 150+ years of German Parliamentary Debates on Migration Reveals Shift from Post-War Solidarity to Anti-Solidarity in the Last Decade

2025-09-08

AI Summary

This study investigates the diachronic evolution of “solidarity” and “anti-solidarity” attitudes in German parliamentary discourse on immigration over 150 years. Addressing the low efficiency and narrow coverage of traditional manual annotation, it conducts the first systematic evaluation of large language models (LLMs) for automated classification of solidarity/anti-solidarity subtypes in German political texts. The study comparatively assesses model scale, prompting strategies, and fine-tuning approaches, empirically validating performance on several thousand manually annotated utterances. Results reveal a dominant solidarity orientation in parliamentary speech from the post-WWII period until 2015, followed by a sharp rise in anti-solidarity rhetoric thereafter. Beyond confirming LLMs’ efficacy for longitudinal sentiment and ideological analysis in historical political corpora, the work delivers a reproducible, automated framework—enabling scalable, cross-national, long-term ideological tracking.

Technology Category

• Natural Language Processing: (Large) Language Models
• Machine Learning: Large Multimodal Models (LMMs)
• Application Domains: Humanities & Computational Social Science

Application Category

• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Economics, Online Markets and Human Computation: Humans versus LLMs for data annotation and labeling

Abstract

Migration has been a core topic in German political debate, from millions of expellees post World War II over labor migration to refugee movements in the recent past. Studying political speech regarding such wide-ranging phenomena in depth traditionally required extensive manual annotations, limiting the scope of analysis to small subsets of the data. Large language models (LLMs) have the potential to partially automate even complex annotation tasks. We provide an extensive evaluation of a multiple LLMs in annotating (anti-)solidarity subtypes in German parliamentary debates compared to a large set of thousands of human reference annotations (gathered over a year). We evaluate the influence of model size, prompting differences, fine-tuning, historical versus contemporary data; and we investigate systematic errors. Beyond methodological evaluation, we also interpret the resulting annotations from a social science lense, gaining deeper insight into (anti-)solidarity trends towards migrants in the German post-World War II period and recent past. Our data reveals a high degree of migrant-directed solidarity in the postwar period, as well as a strong trend towards anti-solidarity in the German parliament since 2015, motivating further research. These findings highlight the promise of LLMs for political text analysis and the importance of migration debates in Germany, where demographic decline and labor shortages coexist with rising polarization.

Problem

• Analyzing solidarity trends in German migration debates
• Automating annotation of parliamentary speeches using LLMs
• Detecting shifts from post-war solidarity to recent anti-solidarity

Innovation

• LLMs automate annotation of parliamentary debates
• Evaluates model size, prompting, fine-tuning effects
• Analyzes historical solidarity trends using AI