LLM-Based Bot Broadens the Range of Arguments in Online Discussions, Even When Transparently Disclosed as AI

TL;DR

This study demonstrates that an AI-powered bot can effectively broaden the range of arguments in online political discussions without reducing transparency, potentially enhancing democratic engagement.

Contribution

It introduces a novel LLM-based moderation bot that actively expands discussion perspectives and shows that transparency about AI identity does not diminish its effectiveness.

Findings

The bot significantly increased the diversity of arguments.

Disclosure of AI identity did not affect the bot's impact.

The approach can positively influence online political discourse.

Abstract

A wide range of participation is essential for democracy, as it helps prevent the dominance of extreme views, erosion of legitimacy, and political polarization. However, engagement in online political discussions often features a limited spectrum of views due to high levels of self-selection and the tendency of online platforms to facilitate exchanges primarily among like-minded individuals. This study examines whether an LLM-based bot can widen the scope of perspectives expressed by participants in online discussions through two pre-registered randomized experiments conducted in a chatroom. We evaluate the impact of a bot that actively monitors discussions, identifies missing arguments, and introduces them into the conversation. The results indicate that our bot significantly expands the range of arguments, as measured by both objective and subjective metrics. Furthermore, disclosure of the bot as AI does not significantly alter these effects. These findings suggest that LLM-based moderation tools can positively influence online political discourse.