Using Language Models for Classifying the Party Affiliation of Political Texts

Abstract

We analyze the use of language models for political text classification. Political texts become increasingly available and language models have succeeded in various natural language processing tasks. We apply two baselines and different language models to data from the UK, Germany, and Norway. Observed accuracy shows language models improving on the performance of the baselines by up to 10.35 % (Norwegian), 12.95 % (German), and 6.39 % (English).

Open Discourse: Towards the first fully Comprehensive and Annotated Corpus of the Parliamentary Protocols of the German Bundestag

“…The temporal coverage makes Open Discourse suitable for longitudinal analyses, while the available meta information allows several differentiated levels of analysis by (dis)aggregating the data tables. At the time of publication, there are already published scientific contributions that utilize Open Discourse (Doan et al 2022) as well as mentioning the lack of the data paper (Blätte et al 2022), which should be solved with this publication. Building on that, Open Discourse's goal of being a meaningful non-profit contribution for democratizing the access to political topics should hopefully enable and assist further research plans in the future.…”