Divergent Paths to Depolarization: Dialogue Design Determines the Prosocial Benefits of AI-Assisted Political Argumentation
2026-05-22 • Computers and Society
Computers and SocietyHuman-Computer Interaction
AI summaryⓘ
The authors studied how talking with an AI chatbot about political issues affects people's feelings and opinions. They found that when people argued using their own views with the AI, it immediately reduced how much they disliked others with different opinions. When people argued against their own views, it didn't help right away but did increase their ability to understand others' perspectives after a couple of weeks. This shows that the way AI conversations are set up matters for reducing political divisions.
argumentative dialoguespolitical polarizationAI chatbotsaffective polarizationcognitive empathyattitude-congruent argumentsattitude-incongruent argumentsbehavioral interventionshuman-AI interaction
Authors
Jianlong Zhu, Syed Muhammad Jhon Raza Naqvi, Carolin-Theresa Ziemer, Usman Naseem, Ingmar Weber
Abstract
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.