用检索增强生成技术分析社交媒体疫苗疑虑，提升公共健康应对精度
Bridging the Gap: Leveraging Retrieval-Augmented Generation to Better Understand Public Concerns about Vaccines
- 结合检索与生成，动态整合最新社媒信息回答复杂疑问
- 在3.5万条疫苗帖子中实现0.96的答非所问率与0.94的相关性
- 适合公共卫生管理者快速掌握公众真实关切
疫苗犹豫威胁公共健康，导致疫苗接种延迟或拒绝。社交媒体是了解公众关切的重要来源，但传统主题建模难以捕捉细微观点。尽管大语言模型（LLM）擅长问答，却常遗漏最新事件和社区关注点，且存在幻觉问题，影响公共卫生传播效果。为此，我们开发了基于检索增强生成（RAG）的工具VaxPulse Query Corner，用于分析多个在线平台上的复杂疫苗关切问题，助力公共卫生管理者理解公众情绪并制定精准干预措施。在分析35,103条关于Shingrix的社交媒体帖子时，该工具达到0.96的答案忠实度和0.94的相关性。
原文摘要 · Abstract (English)
Vaccine hesitancy threatens public health, leading to delayed or rejected vaccines. Social media is a vital source for understanding public concerns, and traditional methods like topic modelling often struggle to capture nuanced opinions. Though trained for query answering, large Language Models (LLMs) often miss current events and community concerns. Additionally, hallucinations in LLMs can compromise public health communication. To address these limitations, we developed a tool (VaxPulse Query Corner) using the Retrieval Augmented Generation technique. It addresses complex queries about public vaccine concerns on various online platforms, aiding public health administrators and stakeholders in understanding public concerns and implementing targeted interventions to boost vaccine confidence. Analysing 35,103 Shingrix social media posts, it achieved answer faithfulness (0.96) and relevance (0.94).
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。