|
View: |
Part 1: Document Description
|
|
Citation |
|
|---|---|
|
Title: |
Replication Data for: Mapping (A)Ideology: A Taxonomy of European Parties Using Generative LLMs as Zero-Shot Learners |
|
Identification Number: |
doi:10.7910/DVN/SECNCZ |
|
Distributor: |
Harvard Dataverse |
|
Date of Distribution: |
2025-02-19 |
|
Version: |
1 |
|
Bibliographic Citation: |
Di Leo, Riccardo; Zeng, Chen; Dinas, Elias; Tamtam, Reda, 2025, "Replication Data for: Mapping (A)Ideology: A Taxonomy of European Parties Using Generative LLMs as Zero-Shot Learners", https://doi.org/10.7910/DVN/SECNCZ, Harvard Dataverse, V1 |
|
Citation |
|
|
Title: |
Replication Data for: Mapping (A)Ideology: A Taxonomy of European Parties Using Generative LLMs as Zero-Shot Learners |
|
Identification Number: |
doi:10.7910/DVN/SECNCZ |
|
Authoring Entity: |
Di Leo, Riccardo (European University Institute) |
|
Zeng, Chen (European University Institute) |
|
|
Dinas, Elias (European University Institute) |
|
|
Tamtam, Reda (European University Institute) |
|
|
Producer: |
<i>Political Analysis</i> |
|
Distributor: |
Harvard Dataverse |
|
Access Authority: |
Di Leo, Riccardo |
|
Depositor: |
Shi, Dihan |
|
Date of Deposit: |
2025-02-19 |
|
Holdings Information: |
https://doi.org/10.7910/DVN/SECNCZ |
|
Study Scope |
|
|
Keywords: |
Social Sciences |
|
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 (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. |
|
Methodology and Processing |
|
|
Sources Statement |
|
|
Data Access |
|
|
Other Study Description Materials |
|
|
Related Publications |
|
|
Citation |
|
|
Title: |
Forthcoming, Political Analysis |
|
Bibliographic Citation: |
Forthcoming, Political Analysis |
|
Label: |
Mapping (A)Ideology.zip |
|
Notes: |
application/zip |