Artificially intelligent opinion polling
Royal Society Open Science · 18.03.2026 · 13 (3)
DOI: 10.1098/rsos.251150 ↗Kurz gefasst
Fachartikel in der Zeitschrift Royal Society Open Science, online erschienen am 18.03.2026. Verfasst von Roberto Cerina und 1 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 150 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Nuffield College, University of Oxford.
Abstract (Originalsprache)
We present a method for using large language models (LLMs) to conduct public opinion polling with social media data. We sample accounts in the run-up to the 2020 US Presidential election based on recent posts related to the major-party candidates. An LLM extracts structured, survey-like data—including socio-demographic characteristics and voting behaviour—from these digital traces. We show that LLM labelling tends to agree with human raters with respect to characteristics of online users. The labelled social media accounts are mapped to a stratification frame, which facilitates MrP estimation of presidential vote share at the state level. We improve this model-based pre-election polling for severely biased online samples by introducing a bias-correction term. The end-to-end implementation takes unrepresentative, unstructured social media data as inputs and produces timely high-quality area-level estimates as outputs. This is artificially intelligent opinion polling. We show that our artificial intelligence (AI) polling estimates of the 2020 election are highly accurate, on par with estimates produced by state-level polling aggregators such as FiveThirtyEight, or from models fit to extremely expensive high-quality samples.
Förderung
- Nuffield College, University of Oxford
Zitieren
APA
Cerina, R., & Duch, R. M. (2026). Artificially intelligent opinion polling. Royal Society Open Science, 13(3). https://doi.org/10.1098/rsos.251150
Vancouver
Cerina R, Duch RM. Artificially intelligent opinion polling. Royal Society Open Science. 2026;13(3). doi:10.1098/rsos.251150
BibTeX
@article{Cerina2026,
author = {Cerina, Roberto and Duch, Raymond M.},
title = {Artificially intelligent opinion polling},
journal = {Royal Society Open Science},
year = {2026},
volume = {13},
number = {3},
doi = {10.1098/rsos.251150}
}
EUVIMED