Can ChatGPT accurately identify the position of parties? A validation study with an expert survey in France
Bibliographic Data
| ID | 6448510 |
|---|---|
| Authors | Damien Bol (0000-0002-1896-1294, Centre de Recherches Politiques de Sciences Po), Pierre-Henri Bono (0009-0003-0077-4794, Centre de Recherches Politiques de Sciences Po) |
| Year | 2025 |
| Volume | 12 |
| Issue | 2 |
| Publication date | 2025-04-01 |
| Open Access | Yes |
| Type | ARTICLE |
| Venue | Research & Politics (JOURNAL) |
| Journal identifiers | ISSN: 2053-1680 • E-ISSN: 2053-1680 |
| Publisher | SAGE Publishing (PUBLISHER • US) |
| DOI | 10.1177/20531680251335653 |
| OpenAlex | W4409591258 |
| Language | EN |
| Citations received | 2 |
| References cited | 28 |
We evaluate whether ChatGPT can be used to estimate the ideological positions of parties in real time. Compared to other methods, ChatGPT can be used at all times, with minimal cost, no technical skills, and for all parties, including new ones. In a validation exercise, we asked ChatGPT and a group of local experts to simultaneously estimate the positions of French political parties in the context of the 2024 European election on a series of issues from the Chapel Hill Expert Survey. We find that ChatGPT’s estimations are generally close to those of the expert survey, especially for major and salient political issues (left-right, European integration, immigration). However, it provides less accurate estimates on fringe issues (free market, asylum policies, urban–rural interests) and specific party characteristics (within-party division, issue blurring). Thus, ChatGPT shows strong potential as an alternative data source for estimating parties’ positions but should be used with caution
Business · Data science · Political science · Position (finance · Computational and Text Analysis Methods · Computer Science · Electoral Systems and Political Participation · Populism, Right-Wing Movements · Psychology
Party Policy in Modern Democracies
Mapping Policy Preferences
Can Generative AI improve social science?
An economic theory of democracy
The Sage Handbook of Electoral Behaviour
The Changing American Voter
Do AIs know what the most important issue is? Using language models to code open-text social survey responses at scale
Ain’t no party like a GPT party
More human than human
Crossvalidating data on party positioning on European integration
Policy Adjustment by Parties in Response to Rival Parties’ Policy Shifts
What to Do (and Not to Do) with the Comparative Manifestos Project Data
Placebo Selection in Survey Experiments
Mean voter representation and partisan constituency representation
Going Negative, Worldwide
Who’s Cueing Whom
Reliability and validity of the 2002 and 2006 Chapel Hill expert surveys on party positioning
Left–Right Political Scales
Going green
Measuring Populism in Political Parties
A Scaling Model for Estimating Time‐Series Party Positions from Texts
What Are Elections For? Conferring the Median Mandate
Conceptual and Measurement Issues in Assessing Democratic Backsliding
Measuring Democratic Backsliding
Niche Party Success and Mainstream Party Policy Shifts - How Green and Radical Right Parties Differ in Their Impact
Chapel Hill Expert Survey trend file, 1999-2019
Extracting Policy Positions from Political Texts Using Words as Data
| Citations per year | 2 |
|---|---|
| Citation span | 2025 - 2026 (2) |
| Highly cited | No |