A rapidly increasing amount of human conversation occurs online. But divisiveness and conflict can fester in text-based interactions on social media platforms, in messaging apps, and on other digital forums. Such toxicity increases polarization and, importantly, corrodes the capacity of diverse societies to develop efficient solutions to complex social problems that impact everyone. Scholars and civil society groups promote interventions that can make interpersonal conversations less divisive or more productive in offline settings, but scaling these efforts to the amount of discourse that occurs online is extremely challenging. We present results of a large-scale experiment that demonstrates how online conversations about divisive topics can be improved with artificial intelligence tools. Specifically, we employ a large language model to make real-time, evidence-based recommendations intended to improve participants' perception of feeling understood in conversations. We find that these interventions improve the reported quality of the conversation, reduce political divisiveness, and improve the tone, without systematically changing the content of the conversation or moving people's policy attitudes. These findings have important implications for future research on social media, political deliberation, and the growing community of scholars interested in the place of artificial intelligence within computational social science.

翻译：在线人类对话量正快速增长。然而，社交媒体平台、即时通讯应用及其他数字论坛中的文本交互容易滋生分歧与冲突。这种毒性言论加剧了社会极化，更重要的是，它侵蚀了多元社会为影响所有人的复杂社会问题制定有效解决方案的能力。学者与公民社会团体致力于推广旨在降低线下人际对话分歧性、提升对话效能的干预措施，但将这些努力规模化应用于线上海量话语交流面临极大挑战。我们通过大规模实验证明，人工智能工具能够改善关于分歧性话题的线上对话质量。具体而言，我们采用大语言模型实时提供基于证据的建议，旨在提升对话者感受到被理解的程度。研究发现，这些干预措施能提升对话报告质量、降低政治分歧、改善对话语气，且不会系统性改变对话内容或改变人们政策态度。这些发现对社交媒体研究、政治审议领域以及日益壮大的计算社会科学中人工智能应用研究团体具有重要启示。