Open Access
Mapping (A)Ideology : a taxonomy of European parties using generative LLMs as zero-shot learners
Loading...
Files
Mapping_Ideology_2025.pdf (816.67 KB)
Full-text in Open Access, Published version
License
Attribution 4.0 International
Cadmus Permanent Link
Full-text via DOI
ISBN
ISSN
1047-1987; 1476-4989
Issue Date
Type of Publication
LC Subject Heading
Other Topic(s)
EUI Research Cluster(s)
Initial version
Published version
Succeeding version
Preceding version
Published version part
Earlier different version
Initial format
Citation
Political analysis, 2025, OnlineFirst
[POSTNORM]
Cite
DI LEO, Riccardo, ZENG, Chen, DINAS, Elias, TAMTAM, Reda, Mapping (A)Ideology : a taxonomy of European parties using generative LLMs as zero-shot learners, Political analysis, 2025, OnlineFirst, [POSTNORM] - https://hdl.handle.net/1814/92572
Abstract
We perform the first mapping of the ideological positions of European parties using generative Artificial Intelligence (AI) as a “zero-shot” learner. We ask OpenAI’s Generative Pre-trained Transformer 3.5 (GPT-3.5) to identify the more “right-wing” option across all possible duplets of European parties at a given point in time, solely based on their names and country of origin, and combine this information via a Bradley–Terry model to create an ideological ranking. A cross-validation employing widely-used expert-, manifesto- and poll-based estimates reveals that the ideological scores produced by Large Language Models (LLMs) closely map those obtained through the expert-based evaluation, i.e., CHES. Given the high cost of scaling parties via trained coders, and the scarcity of expert data before the 1990s, our finding that generative AI produces estimates of comparable quality to CHES supports its usage in political science on the grounds of replicability, agility, and affordability.
Table of Contents
Additional Information
Published online: 14 April 2025
External Links
Publisher
Version
Research Projects
European Commission, 101088868
Sponsorship and Funder Information
This project has received funding from the European Research Council (ERC, POSTNORM, grant agreement No 101088868).
This article was published Open Access with the support from the EUI Library through the CRUI - CUP Transformative Agreement (2023-2025)
This article was published Open Access with the support from the EUI Library through the CRUI - CUP Transformative Agreement (2023-2025)