Echoes of Unrest: A Multimodal NLP Framework for Early Warning of Fake News and Violence-Driven Mob Activity
Quick Answer
This paper shows that This chapter introduces a multilingual, multimodal NLP framework for early detection of misinformation and violence, utilizing XLM-RoBERTa and CLIP.
Quick Take
This chapter introduces a multilingual, multimodal NLP framework for early detection of misinformation and violence, utilizing XLM-RoBERTa and CLIP. A dataset of 138,256 samples achieved 98% test accuracy, demonstrating the framework's effectiveness in predicting real-world escalation through geospatial signals.
Key Points
- Framework integrates XLM-RoBERTa for text and CLIP for visual embedding.
- Dataset combines 138,256 Bangla and English samples for robust training.
- Achieved 98% test accuracy with strong precision and recall metrics.
- Multimodal approach enhances early detection of misinformation.
- Geospatial signals provide additional insights for anticipating violence.
Paper Resources
📖 Reader Mode
~2 min readAbstract:Rapid growth in social media has transformed global communication by enabling fast information exchange, but it has also accelerated the spread of misinformation. Fake news, manipulated content, and provocative narratives are increasingly linked to social unrest, political instability, and mob violence. Incidents in South Asia and elsewhere demonstrate how false information disseminated via platforms such as Facebook and WhatsApp can trigger real-world harm, often spreading faster than fact-checking efforts can respond. To address this challenge, this chapter presents a multilingual, multimodal Natural Language Processing (NLP) framework for early detection of misinformation and violence-prone dynamics. A fused dataset of 138,256 Bangla and English samples was created by combining multiple benchmark datasets. The framework integrates XLM-RoBERTa for multilingual text representation, CLIP for visual embedding, and a multi-head attention mechanism for multimodal fusion, enhanced with auxiliary features such as sarcasm and geospatial metadata. Experiments on a stratified 30% subset achieved 98% test accuracy with strong precision and recall. The outcomes show the efficacy of multimodal approaches in early misinformation detection and highlight the added value of geospatial signals for anticipating real-world escalation.
| Comments: | Accepted for publication as a book chapter (Taylor & Francis, 2026) |
| Subjects: | Computation and Language (cs.CL); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2607.02734 [cs.CL] |
| (or arXiv:2607.02734v1 [cs.CL] for this version) | |
| https://doi.org/10.48550/arXiv.2607.02734 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Md. Maruf Bangabashi [view email]
[v1]
Thu, 2 Jul 2026 20:05:40 UTC (5,274 KB)
— Originally published at arxiv.org
Want this in your inbox every morning?
Daily brief at your local 8am — bilingual EN/中文, free.
More from arXiv cs.CL
See more →Quantifying Prior Dominance in Systems
The study introduces the Normalized Context Utilization (NCU) metric to evaluate Retrieval-Augmented Generation (RAG) systems, revealing that Small Language Models (SLMs) outperform larger models in factual extraction. The findings indicate that traditional scaling laws yield diminishing returns, with a commercial API frequently failing against adversarial evidence due to systemic confidence collapse.