Distant Reading of the German Coalition Deal: Recognizing Policy Positions with BERT-based Text Classification

2022/12/30 by Zylla, Michael, Haider, Thomas
#Computation and Language (cs.CL) #FOS: Computer and information sciences

paper · doi:10.48550/arxiv.2212.14648

Abstract

Automated text analysis has become a widely used tool in political science. In this research, we use a BERT model trained on German party manifestos to identify the individual parties' contribution to the coalition agreement of 2021.

Related

• Electoral Programs of German Parties 2021: A Computational Analysis Of Their Comprehensibility and Likeability Based On SentiArt
• Positions, Factions and Mandates: Applying Quantitative Text Analysis to Self-Reported Biographical Notes from the Members of the 17th German Bundestag
• Analyzing German Parliamentary Speeches: A Machine Learning Approach for Topic and Sentiment Classification
• Annex - Positions, Factions and Mandates: Applying Quantitative Text Analysis to Self-Reported Biographical Notes from the Members of the 17th German Bundestag
• Which Identities Are Mobilized: Towards an automated detection of social group appeals in political texts