Detecting Actionable Requests and Offers on Social Media During Crises Using LLMs
Proceedings of the International ISCRAM Conference · 06.05.2025
DOI: 10.59297/r9q00255 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the International ISCRAM Conference, online erschienen am 06.05.2025. Verfasst von Ahmed El Fekih Zguir und 2 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref).
Abstract (Originalsprache)
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.
Zitieren
APA
Zguir, A. E. F., Ofli, F., & Imran, M. (2025). Detecting Actionable Requests and Offers on Social Media During Crises Using LLMs. Proceedings of the International ISCRAM Conference. https://doi.org/10.59297/r9q00255
Vancouver
Zguir AEF, Ofli F, Imran M. Detecting Actionable Requests and Offers on Social Media During Crises Using LLMs. Proceedings of the International ISCRAM Conference. 2025. doi:10.59297/r9q00255
BibTeX
@article{Zguir2025,
author = {Zguir, Ahmed El Fekih and Ofli, Ferda and Imran, Muhammad},
title = {Detecting Actionable Requests and Offers on Social Media During Crises Using LLMs},
journal = {Proceedings of the International ISCRAM Conference},
year = {2025},
doi = {10.59297/r9q00255}
}
EUVIMED