Comparing and Modeling Argumentation in German Political Communication across Arenas

2026-07-31

AI Summary

This study addresses the lack of computational analysis comparing argumentative patterns across distinct political discourse settings within a unified thematic framework. The authors construct a German-language political corpus comprising 17,000 sentences centered on the COVID-19 pandemic and manually annotate argument boundaries and reason types in three institutional contexts: plenary sessions, committee meetings, and press conferences. For the first time, they systematically compare argument structures across these domains, revealing a counterintuitive finding: expert-based reasoning appears significantly more frequently in press conferences than in committee meetings. Additionally, the paper explores automatic argument boundary detection using sequence labeling models, highlighting both the technical challenges involved and the presence of confirmation bias in model predictions.

Abstract

Deliberation, involving the formulation and exchange of arguments, forms an integral part of political decision making in democracies. Argumentation patterns however differ substantially across different political arenas, such as plenary speeches and committee meetings. However, despite a lot of interest in argumentation, there is comparatively little computational work on analyzing differences in patterns of political argumentation between arenas. Our work addresses this research gap. First, we present a 17k-sentence corpus with annotation for argumentative passages (argument and their justifications, both their boundaries and their categories) across three German political arenas (plenary speeches, committee meetings, and press conferences), keeping the topic (COVID-19) constant. Our analysis of the corpus finds that contrary to expectations, justification by domain-specific expertise is more frequent in press conferences than in committee meetings. Second, we present a pilot study on automatically identifying such argumentative passages. The results show that boundaries are hard to pin down, and models predictions additionally suffer from confirmation bias.

Problem

• political argumentation
• argumentation patterns
• computational analysis
• political arenas
• argument annotation

Innovation

• argumentation mining
• political discourse
• corpus annotation
• computational modeling
• cross-arena comparison