Analyzing German Parliamentary Speeches: A Machine Learning Approach for Topic and Sentiment Classification

TL;DR

This paper develops machine learning models to classify topics and sentiment in 28,000 German parliamentary speeches, revealing insights into political discourse, party dynamics, and ideological shifts over five years.

Contribution

It introduces new machine learning models for topic and sentiment classification tailored to German parliamentary speeches, with high performance and application to political analysis.

Findings

Strong classification performance with AUROC of 0.94 for topics and 0.89 for sentiment

Identifies shifts in discourse style when parties move from government to opposition

Reveals relationships between parties, topics, and sentiment over time

Abstract

This study investigates political discourse in the German parliament, the Bundestag, by analyzing approximately 28,000 parliamentary speeches from the last five years. Two machine learning models for topic and sentiment classification were developed and trained on a manually labeled dataset. The models showed strong classification performance, achieving an area under the receiver operating characteristic curve (AUROC) of 0.94 for topic classification (average across topics) and 0.89 for sentiment classification. Both models were applied to assess topic trends and sentiment distributions across political parties and over time. The analysis reveals remarkable relationships between parties and their role in parliament. In particular, a change in style can be observed for parties moving from government to opposition. While ideological positions matter, governing responsibilities also shape discourse. The analysis directly addresses key questions about the evolution of topics, sentiment dynamics, and party-specific discourse strategies in the Bundestag.