用大模型结合心理学理论，识别网上说服力强的文本。
A Hybrid Theory and Data-driven Approach to Persuasion Detection with Large Language Models
- 用大模型生成心理特征评分，构建分类模型预测说服效果。
- 情感认知与分享意愿是影响信念改变的两大关键因素。
- 适合研究网络影响力、假信息治理和叙事效果评估的人参考。
传统信念修正的心理学模型主要针对面对面交流，但社交媒体兴起后，亟需更有效的模型来捕捉大规模、基于文本的在线讨论中的信念变化。本文采用混合方法，利用大语言模型（LLMs）生成文献中已有研究的心理特征评分，构建随机森林分类模型，预测消息是否引发信念改变。在测试的八项特征中，'认知情感'（epistemic emotion）和'分享意愿'（willingness to share）是模型中预测效果最好的两个变量。研究揭示了具有说服力文本的关键特征，展示了如何借助大模型增强基于心理学理论的说服力预测模型。这些发现可广泛应用于在线影响力检测、虚假信息防控及网络叙事有效性评估。
原文摘要 · Abstract (English)
Traditional psychological models of belief revision focus on face-to-face interactions, but with the rise of social media, more effective models are needed to capture belief revision at scale, in this rich text-based online discourse. Here, we use a hybrid approach, utilizing large language models (LLMs) to develop a model that predicts successful persuasion using features derived from psychological experiments. Our approach leverages LLM generated ratings of features previously examined in the literature to build a random forest classification model that predicts whether a message will result in belief change. Of the eight features tested, \textit{epistemic emotion} and \textit{willingness to share} were the top-ranking predictors of belief change in the model. Our findings provide insights into the characteristics of persuasive messages and demonstrate how LLMs can enhance models of successful persuasion based on psychological theory. Given these insights, this work has broader applications in fields such as online influence detection and misinformation mitigation, as well as measuring the effectiveness of online narratives.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。