Distant Reading of the German Coalition Deal: Recognizing Policy Positions with BERT-based Text Classification
Michael Zylla, Thomas Haider
TL;DR
This paper employs a BERT-based text classification model trained on German party manifestos to analyze and recognize the policy positions of different parties within the 2021 coalition agreement.
Contribution
It introduces a novel application of BERT for analyzing coalition agreements by training on party manifestos to identify individual party contributions.
Findings
Effective identification of party-specific policy positions
High accuracy in classifying party contributions
Demonstrates the utility of BERT in political text analysis
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.
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsComputational and Text Analysis Methods · Political Influence and Corporate Strategies
MethodsMulti-Head Attention · Attention Is All You Need · Linear Layer · WordPiece · Refunds@Expedia|||How do I get a full refund from Expedia? · Adam · Layer Normalization · Softmax · Linear Warmup With Linear Decay · Residual Connection