利用大语言模型检测危机期间社交媒体上的可执行请求与提供
Detecting Actionable Requests and Offers on Social Media During Crises Using LLMs
AI总结:
提出细粒度分层分类体系与查询特定少样本学习方法,利用大语言模型检测并优先处理危机期间社交媒体上的可执行请求与提供。
摘要:
自然灾害常常导致社交媒体活动激增,其中包括援助请求、帮助提供、情绪表达和一般性更新。为使 humanitarian 组织能够更高效地响应,我们提出了一种细粒度的分层分类体系,将危机相关的请求与提供信息系统地组织到三个关键维度:物资、应急人员和行动。利用大语言模型(LLMs)的能力,我们引入了查询特定少样本学习(QSF Learning),该方法从嵌入数据库中检索类特定的标注示例,以增强模型在检测和分类帖子方面的性能。在分类之外,我们还评估消息的可执行性,以优先处理需要立即关注的帖子。大量实验表明,我们的方法优于基线提示策略,能够有效识别并优先处理可执行的请求与提供。
英文摘要:
Natural disasters often result in a surge of social media activity, including requests for assistance, offers of help, sentiments, and general updates. To enable humanitarian organizations to respond more efficiently, we propose a fine-grained hierarchical taxonomy to systematically organize crisis-related information about requests and offers into three critical dimensions: supplies, emergency personnel, and actions. Leveraging the capabilities of Large Language Models (LLMs), we introduce Query-Specific Few-shot Learning (QSF Learning) that retrieves class-specific labeled examples from an embedding database to enhance the model's performance in detecting and classifying posts. Beyond classification, we assess the actionability of messages to prioritize posts requiring immediate attention. Extensive experiments demonstrate that our approach outperforms baseline prompting strategies, effectively identifying and prioritizing actionable requests and offers.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。