Extracting Disaster Impacts and Impact Related Locations in Social Media Posts Using Large Language Models

2025/11/24 by Sameeah Noreen Hameed, Hameed, Sameeah Noreen, Surangika Ranathunga +7
Social Sciences · #Artificial Intelligence (cs.AI) #Computation and Language (cs.CL) #Disaster Management and Resilience #FOS: Computer and information sciences #Geographic Information Systems Studies #Public Relations and Crisis Communication

paper · pdf · doi:10.48550/arxiv.2511.21753

openalex publication_date 2025/11/24 · openalex created_date 2025/12/03 · openalex updated_date 2026/07/28

Abstract

Large-scale disasters can often result in catastrophic consequences on people and infrastructure. Situation awareness about such disaster impacts generated by authoritative data from in-situ sensors, remote sensing imagery, and/or geographic data is often limited due to atmospheric opacity, satellite revisits, and time limitations. This often results in geo-temporal information gaps. In contrast, impact-related social media posts can act as "geo-sensors" during a disaster, where people describe specific impacts and locations. However, not all locations mentioned in disaster-related social media posts relate to an impact. Only the impacted locations are critical for directing resources effectively. e.g., "The death toll from a fire which ripped through the Greek coastal town of #Mati stood at 80, with dozens of people unaccounted for as forensic experts tried to identify victims who were burned alive #Greecefires #AthensFires #Athens #Greece." contains impacted location "Mati" and non-impacted locations "Greece" and "Athens". This research uses Large Language Models (LLMs) to identify all locations, impacts and impacted locations mentioned in disaster-related social media posts. In the process, LLMs are fine-tuned to identify only impacts and impacted locations (as distinct from other, non-impacted locations), including locations mentioned in informal expressions, abbreviations, and short forms. Our fine-tuned model demonstrates efficacy, achieving an F1-score of 0.69 for impact and 0.74 for impacted location extraction, substantially outperforming the pre-trained baseline. These robust results confirm the potential of fine-tuned language models to offer a scalable solution for timely decision-making in resource allocation, situational awareness, and post-disaster recovery planning for responders.

Citations

• Layer-0 Suppressors Ground Hallucination Inevitability: A Mechanistic Account of How Transformers Trade Factuality for Hedging
• Do LLMs Surpass Encoders for Biomedical NER?
• Evaluating Robustness of LLMs on Crisis-Related Microblogs across Events, Information Types, and Linguistic Features
• Zero-Shot Classification of Crisis Tweets Using Instruction-Finetuned Large Language Models
• LLM-DER:A Named Entity Recognition Method Based on Large Language Models for Chinese Coal Chemical Domain
• Monitoring Critical Infrastructure Facilities During Disasters Using Large Language Models
• Large Language Models for Generative Information Extraction: A Survey
• GLiNER: Generalist Model for Named Entity Recognition using Bidirectional Transformer
• A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questions
• Chain-of-Verification Reduces Hallucination in Large Language Models
• A Survey of Hallucination in Large Foundation Models
• PromptNER: Prompting For Named Entity Recognition
• GPT-NER: Named Entity Recognition via Large Language Models
• Emergent Abilities of Large Language Models
• Survey of Hallucination in Natural Language Generation
• BNAI, NO-TOKEN, and MIND-UNITY: Pillars of a Systemic Revolution in Artificial Intelligence
• Identification of Fine-Grained Location Mentions in Crisis Tweets
• Pre-train, Prompt, and Predict: A Systematic Survey of Prompting Methods in Natural Language Processing
• Pre-train, Prompt, and Predict: A Systematic Survey of Prompting Methods in Natural Language Processing
• HumAID: Human-Annotated Disaster Incidents Data from Twitter with Deep Learning Benchmarks
• Calibrate Before Use: Improving Few-Shot Performance of Language Models
• It's Not Just Size That Matters: Small Language Models Are Also Few-Shot\n Learners
• Language Models are Few-Shot Learners
• CrisisBERT: a Robust Transformer for Crisis Classification and Contextual Crisis Embedding
• Unsupervised Cross-lingual Representation Learning at Scale
• Calibration, Entropy Rates, and Memory in Language Models
• Location reference identification from tweets during emergencies: A deep learning approach
• Big data analytics for disaster response and recovery through sentiment analysis
• A Twitter Tale of Three Hurricanes: Harvey, Irma, and Maria
• SAVITR: A System for Real-time Location Extraction from Microblogs during Emergencies
• Twitter as a Lifeline: Human-annotated Twitter Corpora for NLP of Crisis-related Messages
• Neural Architectures for Named Entity Recognition
• Processing Social Media Messages in Mass Emergency: A Survey
• Aligning Large Language Models with Human: A Survey
• BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding

Related

• Monitoring Critical Infrastructure Facilities During Disasters Using Large Language Models
• DisasterTD: Disaster Toponym Disambiguation Using Multimodal LLMs and Cross-View Geolocalization
• A multimodal GeoAI approach to combining text with spatiotemporal features for enhanced relevance classification of social media posts in disaster response
• Extracting Large Scale Spatio-Temporal Descriptions from Social Media
• Investigating disaster response through social media data and the Susceptible-Infected-Recovered (SIR) model: A case study of 2020 Western U.S. wildfire season