Can LLMs Follow the Pulse of a Crisis? Evaluating Crisis Sentiment in Bangladesh's July Uprising

2026-09-15

AI Summary

研究通过构建UNRESTSENT200K数据集，利用细调编码器、提示LLM和LoRA调整的LLM方法，解决孟加拉语危机情感分析问题。

Abstract

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 sentiment dataset with approximately 200K Facebook and YouTube comments from the July-August 2024 Bangladesh uprising. The dataset covers five event-aligned phases, from early escalation and internet blackout to regime transition and a later flood crisis. Each comment is linked to its parent post, enabling evaluation with and without discourse context. All comments are annotated through a fully human process involving 14 native Bangla-speaking annotators and senior validation, achieving substantial agreement (kappa = 0.73, alpha = 0.71) and 94.2% blind-audit agreement. We benchmark fine-tuned encoders, prompted LLMs, and LoRA-tuned LLMs. Results show that parent-post context consistently improves performance, while temporal shift across phases causes large performance drops. Strong LLMs perform well, but still struggle with sarcasm, implicit political references, and phase-dependent meaning. UNRESTSENT200K provides a benchmark for studying context-aware and temporally robust sentiment analysis in low-resource crisis discourse. UNRESTSENT200K is available at https://sami0055.github.io/UNRESTSENT200K/

Problem

• Crisis Sentiment Analysis
• Low-Resource Languages
• Bangla
• Context Shift
• Public Reaction

Innovation

• UNRESTSENT200K
• crisis sentiment analysis
• context-aware
• temporally robust
• low-resource language