Divergent Paths to Depolarization: Dialogue Design Determines the Prosocial Benefits of AI-Assisted Political Argumentation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zhu, Jianlong, Naqvi, Syed Muhammad Jhon Raza, Ziemer, Carolin-Theresa, Naseem, Usman, Weber, Ingmar
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910248881618944
author Zhu, Jianlong
Naqvi, Syed Muhammad Jhon Raza
Ziemer, Carolin-Theresa
Naseem, Usman
Weber, Ingmar
author_facet Zhu, Jianlong
Naqvi, Syed Muhammad Jhon Raza
Ziemer, Carolin-Theresa
Naseem, Usman
Weber, Ingmar
contents Argumentative dialogues across political divides can reduce polarization, yet opportunities for citizens to engage with opposing views in accessible and structured ways remain limited. AI dialogue partners offer a scalable framework for such open-mindedness exercises, but how the format of human-AI dialogues shapes their benefits remains unclear. In a two-session online experiment, 469 US participants were assigned to argue either for or against their own attitude on a contested political issue with an AI chatbot. Our experimental findings show attitude-congruent dialogues produced greater immediate reduction in both affective and opinion polarization than attitude-incongruent dialogues. By contrast, attitude-incongruent dialogues elicited weaker cognitive state empathy than the non-AI reference task but increased cognitive trait empathy in the two-week period between sessions, suggesting the effects of active generation of attitude-incongruent arguments may emerge over time. These findings highlight dialogue design as a key determinant of effective AI-mediated behavioral interventions.
format Preprint
id arxiv_https___arxiv_org_abs_2605_23890
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Divergent Paths to Depolarization: Dialogue Design Determines the Prosocial Benefits of AI-Assisted Political Argumentation
Zhu, Jianlong
Naqvi, Syed Muhammad Jhon Raza
Ziemer, Carolin-Theresa
Naseem, Usman
Weber, Ingmar
Computers and Society
Human-Computer Interaction
Argumentative dialogues across political divides can reduce polarization, yet opportunities for citizens to engage with opposing views in accessible and structured ways remain limited. AI dialogue partners offer a scalable framework for such open-mindedness exercises, but how the format of human-AI dialogues shapes their benefits remains unclear. In a two-session online experiment, 469 US participants were assigned to argue either for or against their own attitude on a contested political issue with an AI chatbot. Our experimental findings show attitude-congruent dialogues produced greater immediate reduction in both affective and opinion polarization than attitude-incongruent dialogues. By contrast, attitude-incongruent dialogues elicited weaker cognitive state empathy than the non-AI reference task but increased cognitive trait empathy in the two-week period between sessions, suggesting the effects of active generation of attitude-incongruent arguments may emerge over time. These findings highlight dialogue design as a key determinant of effective AI-mediated behavioral interventions.
title Divergent Paths to Depolarization: Dialogue Design Determines the Prosocial Benefits of AI-Assisted Political Argumentation
topic Computers and Society
Human-Computer Interaction
url https://arxiv.org/abs/2605.23890