Mapping (A)Ideology: A Taxonomy of European Parties Using Generative LLMs as Zero-Shot Learners

TY - JOUR

T1 - Mapping (A)Ideology: A Taxonomy of European Parties Using Generative LLMs as Zero-Shot Learners

AU - Di Leo, Riccardo

AU - Zeng, Chen

AU - Dinas, Elias

AU - Tamtam, Reda

N1 - Publisher Copyright: © The Author(s), 2025.

PY - 2025/4/14

Y1 - 2025/4/14

N2 - 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.

AB - 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.

UR - http://www.scopus.com/inward/record.url?scp=105002693320&partnerID=8YFLogxK

U2 - 10.1017/pan.2025.7

DO - 10.1017/pan.2025.7

M3 - Article

SN - 1047-1987

VL - First View

JO - POLITICAL ANALYSIS

JF - POLITICAL ANALYSIS

IS - 2025

ER -