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

Riccardo Di Leo, Chen Zeng, Elias Dinas, and Reda Tamtam

Forthcoming in Political Analysis

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 (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 decomposition 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 first, i.e., CHES. Given the high cost of scaling parties via trained coders, and the scarcity of expert data before the 1990s, 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.

The geography of trade: Economic shocks, regional competitiveness, and support for trade in the UK

Sofia Vasilopoulou, Chen Zeng, Dan Keith, and Liisa Talving

Manuscript in preparation