Crises alter both how people move and how they communicate. During emergencies such as wildfires and pandemics, changes in mobility patterns and online emotional discourse evolve jointly, yet they are typically studied in isolation.
arXiv:2405. 17838v3 Announce Type: replace-cross Abstract: Socio-linguistic indicators of affectively-relevant phenomena, such as emotion or sentiment, are often extracted from text to better understand features of human-computer interactions, including on social media.
Effective crisis response requires spatially grounded communication that bridges linguistic guidance of civilians with the physical environment, accounting for structural bottlenecks, evolving threats, and agent-specific contexts. Yet, current NLP research in crisis communication remains mainly limited to static, text-only classification settings, overlooking the critical communicative role of AI operators in dynamic, embodied scenarios.
arXiv:2609.16997v1 Announce Type: new Abstract: Crisis sentiment analysis is especially challenging for low-resource languages such as Bangla, where language, context, and public reaction shift rapid...
arXiv:2607. 13260v1 Announce Type: cross Abstract: Policy documents shape governance outcomes, but their reasoning is often implicit.
arXiv:2606. 10380v1 Announce Type: cross Abstract: Real-world crisis intervention is inherently conversational, yet existing research largely focuses on static texts.
arXiv:2602. 13452v2 Announce Type: replace-cross Abstract: Large language models (LLMs) are increasingly proposed for crisis preparedness and response, particularly for multilingual communication.
arXiv:2607. 02734v1 Announce Type: cross Abstract: Rapid growth in social media has transformed global communication by enabling fast information exchange, but it has also accelerated the spread of misinformation.
The paper introduces a two‑stage training framework that combines Supervised Fine‑Tuning (SFT) and Direct Preference Optimization (DPO) to improve multimodal disaster severity assessment. It creates two datasets—ReasoningSet for validated rationales and PreferenceSet for paired rationales—using a single Human‑in‑the‑Loop workflow. Experiments on InternVL‑3‑8B and LLaVA‑1.5‑7B show that SFT boosts classification accuracy and Macro‑F1, while DPO further enhances interpretability and alignment with human judgment.
Crisis sentiment analysis is especially challenging for low-resource languages such as Bangla, where language, context, and public reaction shift rapidly. We introduce UNRESTSENT200K, a Bangla crisis...
arXiv:2608. 14651v1 Announce Type: new Abstract: Effective disaster risk communication is a foundational humanitarian challenge, yet current emergency infrastructure fails to meet the needs of individuals with access and functional needs, including hard-of-hearing individuals, pregnant women, mothers with toddlers, and elderly individuals with dementia.
The paper introduces EMPATH, a framework that analyzes emotion dynamics in crisis counseling dialogues at three levels: turn-level labels, transition probabilities, and global conversation archetypes. Using EMPATH on text-based conversations between Black texters and volunteers about grief, the study reveals persistent negative affect, gradual shifts toward hope, distinct emotional roles for texters and volunteers, and varied recovery paths. These findings demonstrate how dynamic emotion analysis can uncover informative patterns in crisis support interactions.
HUMAID-NER is the first named entity recognition dataset built on the HumAID benchmark, comprising 60,000 English disaster tweets with approximately 175,000 labeled entity spans across ten operationally motivated entity types. The dataset was created using a reproducible three‑stage hybrid pipeline that combines a spaCy transformer model, disaster‑domain EntityRuler patterns, and structured regular expressions with priority‑based overlap resolution. A joint multitask learning framework using a shared RoBERTa‑large encoder and homoscedastic uncertainty weighting achieves an NER span micro‑F1 of 0.841 and classification macro‑F1 of 0.761, and the authors provide a real‑time web dashboard, dataset, models, and pipeline code for reproducibility.