Detecting Actionable Requests and Offers on Social Media During Crises Using LLMs
This work addresses the challenge for humanitarian organizations to efficiently prioritize and respond to critical social media posts during natural disasters, representing a domain-specific incremental improvement.
The paper tackled the problem of detecting and classifying actionable requests and offers on social media during crises by proposing a hierarchical taxonomy and a Query-Specific Few-shot Learning method using LLMs, resulting in outperforming baseline prompting strategies in experiments.
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.