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

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

URL: http://arxiv.org/abs/2609.16997v1
Date: Tue, 15 Sep 2026 11:08:25 GMT
Title: Can LLMs Follow the Pulse of a Crisis? Evaluating Crisis Sentiment in Bangladesh's July Uprising
Abstract summary: We introduce UNRESTSENT200K, a Bangla crisis sentiment dataset with approximately 200K Facebook and YouTube comments from the July-August 2024 Bangladesh uprising.<n>Each comment is linked to its parent post, enabling evaluation with and without discourse context.<n>Results show that parent-post context consistently improves performance, while temporal shift across phases causes large performance drops.
Score: 2.1411735704266
License: http://creativecommons.org/licenses/by/4.0/
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/

Related papers

Advancing All-Weather Building Damage Mapping to the Instance Level: Outcomes and Insights from the 2026 Bright Challenge [51.684701877722574]
Rapid post-disaster response requires timely, building-level information on whether structures remain intact, are damaged, or are destroyed.<n>The Bright Challenge evaluated all-weather building damage mapping from a submeter-resolution pre-event optical image and a post-event SAR image.
arXiv Detail & Related papers (2026-07-23T07:22:15Z)
Beyond Benchmarks: Exposing the Hidden Crisis in Bangla Hate Speech Detection [3.6609212521250227]
Hate speech spread on social media platforms poses a major concern for online safety and ethical moderation.<n>This study aimed to expose the crisis of Bangla HS detection systems by diagnosing how and why benchmark-trained models fail to identify implicit, context-dependent HS.<n>Emoji-aware preprocessing improved implicit HS detection by up to 12%, whereas emoji removal caused a notable decline in performance.
arXiv Detail & Related papers (2026-07-13T14:19:16Z)
Learning to Deny: Action Denial in Multimodal Large Language Models [12.607064466360216]
Multimodal large language models (MLLMs) have rapidly advanced video understanding, achieving strong zero-shot and few-shot recognition across standard benchmarks.<n>Yet their ability to deny an action by recognizing when an activity is not happening despite strong contextual cues remains largely unexplored.<n>We introduce UCF101-AD, a benchmark consisting of paired Action-Presence and Action-Denial clips, designed to evaluate this capacity for denial.
arXiv Detail & Related papers (2026-06-30T06:16:17Z)
Coping in Crisis: Computational Modeling of Coping Styles in Digital Crisis Discourse During the 2023 Turkiye Earthquake [0.0]
This study uses over one million Turkish-language tweets posted in the aftermath of the February 6, 2023 earthquake in Turkiye.<n>We develop a multi-label BERTurk to detect three coping styles across four theoretically motivated crisis phases.<n>Problem-focused coping dominates the urgency phase and declines sharply, emotion-focused coping rises and stabilizes, and meaning-making increases monotonically.
arXiv Detail & Related papers (2026-06-12T12:57:13Z)
Interpretable Crisis Behavior Analysis Using Mobility and Social Media Data [0.981328290471248]
This paper presents a unified and interpretable pipeline that integrates mobility and social media data to identify cross-domain behavioral patterns in crisis settings.<n>The framework is evaluated through two case studies: a short-horizon analysis of the January 2025 Los Angeles wildfires (prototype case) and a longitudinal analysis of UAE COVID-19 behavior from March 2020 to December 2021.
arXiv Detail & Related papers (2026-06-08T14:16:36Z)
When a Nation Speaks: Machine Learning and NLP in People's Sentiment Analysis During Bangladesh's 2024 Mass Uprising [0.4950304764576159]
We pioneer sentiment analysis in Bangla during a national crisis by examining public emotions amid Bangladesh's 2024 mass uprising.<n>We curated a dataset of 2,028 annotated news headlines from major Facebook news portals, classifying them into Outrage, Hope, and Despair.<n>We identified prevalent themes like political corruption and public protests, and analyzed how events such as internet blackouts shaped sentiment patterns.
arXiv Detail & Related papers (2025-12-17T15:54:37Z)
NoLiMa: Long-Context Evaluation Beyond Literal Matching [100.00398424275501]
NoLiMa is a benchmark extending the needle-in-a-haystack (NIAH) test.<n>It requires models to infer latent associations to locate the needle within the haystack.<n>We evaluate 13 popular large language models that claim to support contexts of at least 128K tokens.
arXiv Detail & Related papers (2025-02-07T18:49:46Z)
WikiContradict: A Benchmark for Evaluating LLMs on Real-World Knowledge Conflicts from Wikipedia [59.96425443250666]
Retrieval-augmented generation (RAG) has emerged as a promising solution to mitigate the limitations of large language models (LLMs) In this work, we conduct a comprehensive evaluation of LLM-generated answers to questions based on contradictory passages from Wikipedia. We benchmark a diverse range of both closed and open-source LLMs under different QA scenarios, including RAG with a single passage, and RAG with 2 contradictory passages.
arXiv Detail & Related papers (2024-06-19T20:13:42Z)
LLoCO: Learning Long Contexts Offline [63.3458260335454]
We propose LLoCO, a novel approach to processing long contexts. LLoCO learns contexts offline through context compression and in-domain parameter-efficient finetuning with LoRA. Our approach extends the effective context window of a 4k token LLaMA2-7B model to handle up to 128k tokens.
arXiv Detail & Related papers (2024-04-11T17:57:22Z)
Sentiment Analysis through LLM Negotiations [58.67939611291001]
A standard paradigm for sentiment analysis is to rely on a singular LLM and makes the decision in a single round. This paper introduces a multi-LLM negotiation framework for sentiment analysis.
arXiv Detail & Related papers (2023-11-03T12:35:29Z)
Changes in European Solidarity Before and During COVID-19: Evidence from a Large Crowd- and Expert-Annotated Twitter Dataset [77.27709662210363]
We introduce the well-established social scientific concept of social solidarity and its contestation, anti-solidarity, as a new problem setting to supervised machine learning in NLP. We annotate 2.3k English and German tweets for (anti-)solidarity expressions, utilizing multiple human annotators and two annotation approaches (experts vs. crowds) Our results show that solidarity became increasingly salient and contested during the COVID-19 crisis.
arXiv Detail & Related papers (2021-08-02T17:03:12Z)

This list is automatically generated from the titles and abstracts of the papers in this site.