EU Permacrisis through National Lenses: A Blended Reading Analysis of Austrian and German Election Manifestos (2002-2025) using BERTopic and LLM

Authors

DOI:

https://doi.org/10.15203/4242.vol55.2026

Abstract

The digital age has produced extensive datasets documenting communication by political actors, the media, and civil society, indicating a shift in political discourse toward digital platforms. Election manifestos, for example, are now primarily distributed online through campaign websites. The accessibility of such data has increased due to advances in algorithm-based methods for collecting, storing, and analysing large volumes of digital empirical data. However, greater data volume brings increased complexity. These trends introduce methodological challenges in collection, pre-processing, and analysis. To address these problems, our paper proposes a human-in-the-loop blended reading workflow combining BERTopic with a large language model (LLM), demonstrated through a case study of German and Austrian national parliamentary election campaigns between 2002 and 2025. During this period, elections took place against the backdrop of multiple crises that threatened the European Union’s internal security and democratic foundations. Scholars frequently employ the term permacrisis to characterise this persistent state of crisis and its associated challenges. With our explorative approach, we trace which issues are addressed by the Austrian and German parties in their communication through national election manifestos. This shall further allow us to detect policy fields and to analyse if EU permacrisis events are displayed. 

Author Biographies

  • Florence Ertel, University of Passau

    Florence Ertel is Researcher Jean-Monnet Chair of European Politics and the Chair of Political Communication with a Focus on Eastern Europe and the Post-Soviet Region, both University of Passau, Germany. In addition, she is a lecturer at the Bucharest University of Economic Studies, Romania. Her research focuses on Political Communication, Propaganda, the EU’s external relations with countries in Eastern Europe, the Southern Caucasus and Central Asia, and the Common Security and Defence Policy. Before joining academia, the trained journalist worked for Passauer Neue Presse and Bayer AG.

  • Sebastian Gassner, University of Passau

    Sebastian Gassner is a researcher at the Chair of Computational Humanities at the University of Passau, focusing on digitisation methods in the field of cultural heritage, and natural language processing. He studied Art and Technology at Chalmers University in Gothenburg, Sweden, and is a lecturer for programming. Besides his academic career, he has been working as a Software Engineer for two decades, with a strong focus on problem gambling, large-scale data integration, optimisation and software architecture.

Downloads

Published

2026-03-26

Issue

Vol. 55 No. 1 (2026): Open Issue

Section

Research Article

License

Copyright (c) 2026 Florence Ertel, Sebastian Gassner

Creative Commons License

This work is licensed under a Creative Commons Attribution-ShareAlike 3.0 Unported License.

The OZP is the authorized quarterly publication of the Österreichische Gesellschaft für Politikwissenschaft (ÖGPW, Austrian Political Science Association)

The author of an article (in case of multiple authors: the corresponding author, responsible for releasing this material on behalf of any and all co-authors) accepted to be published in the OZP hereby acknowledges the following Copyright Notice:

  1. The author retains the copyright to the article.
  2. It is the responsibility of the author, not of the OZP, to obtain permission to use any previously published and/or copyrighted material.
  3. Publication of a submitted text is dependent on positive results from the peer reviewing. In such a case, the OZP editors have the right to publish the text.
  4. In case of publication, the article will be assigned a DOI (digital object identifier) number.
  5. The author agrees to abide by an open access Creative Commons Attribution (CC BY nc) license. The license permits any user to download, print out, extract, reuse, archive, and distribute the article in any non-commercial way, so long as appropriate credit is given to the author and source of the work. 
  6. The license ensures that the author’s article will be available as widely as possible and that the article can be included in any scientific archive. In order to facilitate distribution, the author agrees that the article, once published, will be submitted to various abstracting, indexing and archiving services as selected by the OZP.
  7. In addition, the author is encouraged to self-archive the article, once published, with reference to the place of the first publication.
  8. After the contribution appears in the OZP, it is still possible to publish it elsewhere with reference to the place of the first publication.
  9. The finished article, if published, will include a correspondence address (both postal and email) of the author.
  10. If written under the auspices of a grant from one or more funding agencies, such as FWF (Austrian Science Fund), ERC (European Research Council), and Horizon 2020 (EU Framework Programme), an article accepted for publication has to be deposited in an Open Access archive. The OZP’s archiving policy is compliant with these provisions. (In case the article derives on funding from a different source, the author is responsible to check compliance of provisions.)