用GPT-4.1模拟人物观点，预测选举和医疗态度准确率超90%
Evaluating the Effectiveness of Persona Simulation in Opinion Prediction with GPT-4.1
- 用真实人口画像数据让GPT-4.1模拟各州民众观点
- 在8个州成功预测2024选举结果，疫苗态度预测准确率达0.94
- 适合做舆情分析、公共政策预判的AI工具
Persona simulation通过大语言模型基于特定特征信息预测人类选择或互动。我们使用GPT-4.1（知识截止于2024年6月）测试其在观点预测中的效果。基于哥伦比亚大学提供的九个美国州的人物画像数据，GPT-4.1成功预测了其中八个州的2024年选举结果，仅在其中一个摇摆州失败。随后针对医疗与健康议题，利用皮尤研究中心的American Trends Panel Wave 123数据集，GPT-4.1对儿童疫苗态度的预测准确率达到0.94。此外，我们让GPT-4.1生成人物间的对话，发现模拟言论符合人物性格与背景，但缺乏自然的人类表达流。该方法在纠正偏见后，有望应用于从公共卫生到立法决策再到经济分析等领域的观点分析与反应预测。
原文摘要 · Abstract (English)
Persona simulation involves utilizing large language models (LLMs) to anticipate human choices or interactions based on specific characteristic information. To further understand current limitations and future directions, we tested persona simulation in opinion prediction with GPT-4.1 (knowledge cutoff by June 2024). Using personas from nine U.S. states provided by Columbia University's Personas dataset, GPT-4.1 accurately predicted 2024 election outcomes in eight out of the nine states, only failing in one of the swing states. We then focused on opinions related to medicine and healthcare. With the American Trends Panel Wave 123 dataset from Pew Research Center, GPT-4.1 was able to anticipate beliefs about childhood vaccines with an accuracy of up to 0.94. Furthermore, we applied GPT-4.1 to generate conversations among personas and observed that the simulated dialogues and opinions adhered well to personas' personalities and backgrounds, albeit lacking natural human-like flow. Persona simulation proves to be a promising application of artificial intelligence as long as biases are addressed. In the near future, it will be beneficial to apply it to opinion analysis and reaction prediction in diverse fields ranging from public health to lawmaking to economics.
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。