Conviction, persuasiveness, and cross-cutting exposure: a Bayesian model of voting behaviour in online political debates
Abstract
Online debate platforms offer a window into whether exposure to diverse crowds changes how people reason: they capture political preferences, the perceived quality of arguments, and the ideological diversity of the audience. Drawing on theories of deliberative democracy and cross-cutting exposure, I develop a Bayesian logistic regression model that decomposes voting behaviour in online debates into three components: conviction (agreement between a user's prior beliefs and a debate's stance), persuasiveness (perceived argument quality), and cross-cutting exposure (the ideological diversity of a debate's prior voters). I apply this framework to the DDO dataset: approximately 341k votes across 78k debates on 48 socio-political topics. As the platform provides no predefined topic labels, I infer topic and stance from debate text using large language models. I test whether a more ideologically diverse prior audience weakens a voter's conviction, a central claim from the cross-cutting exposure literature. Persuasiveness is the strongest and most consistent predictor of vote choice, never outweighed by conviction, though conviction remains a credible predictor on several topics tied to personal freedoms. Cross-cutting exposure moderates conviction on 4 of 47 topics, though these results are sensitive to topic classification and sparse coverage, with implications for the design of deliberative platforms.
Related
- Fast, cheap and sustainable: armament portfolio arbitration under attrition, lead time and political discontinuity
- On the within-person effects of political attitudes on outgroup animosity: Evidence for Democratic-Republican asymmetry
- Issue Bias in Generative AI Writing Assistance: Political Issues and LLMs in the Swedish 2026 Election
- Forecast-Necessary Causal Discovery for Nonlinear Political Panel Data: Feedback, Functional Form, and the Dynamics of Democratization
- Diversity, Efficiency, and Incentives in Political Prediction Markets
BibTeX
@misc{candellone2026conviction,
title = {{Conviction, persuasiveness, and cross-cutting exposure: a Bayesian model of voting behaviour in online political debates}},
author = {Elena Candellone},
howpublished = {arXiv},
year = {2026},
month = sep,
doi = {10.48550/arxiv.2606.03786},
eprint = {2606.03786},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2606.03786},
note = {CC BY-NC-ND 4.0},
}
RIS
TY - UNPB
TI - Conviction, persuasiveness, and cross-cutting exposure: a Bayesian model of voting behaviour in online political debates
AU - Elena Candellone
PY - 2026
DA - 2026/09/15
PB - arXiv
DO - 10.48550/arxiv.2606.03786
UR - https://arxiv.org/abs/2606.03786
AB - Online debate platforms offer a window into whether exposure to diverse crowds changes how people reason: they capture political preferences, the perceived quality of arguments, and the ideological diversity of the audience. Drawing on theories of deliberative democracy and cross-cutting exposure, I develop a Bayesian logistic regression model that decomposes voting behaviour in online debates into three components: conviction (agreement between a user's prior beliefs and a debate's stance), persuasiveness (perceived argument quality), and cross-cutting exposure (the ideological diversity of a debate's prior voters). I apply this framework to the DDO dataset: approximately 341k votes across 78k debates on 48 socio-political topics. As the platform provides no predefined topic labels, I infer topic and stance from debate text using large language models. I test whether a more ideologically diverse prior audience weakens a voter's conviction, a central claim from the cross-cutting exposure literature. Persuasiveness is the strongest and most consistent predictor of vote choice, never outweighed by conviction, though conviction remains a credible predictor on several topics tied to personal freedoms. Cross-cutting exposure moderates conviction on 4 of 47 topics, though these results are sensitive to topic classification and sparse coverage, with implications for the design of deliberative platforms.
ER -