Artificial Intelligence for Social Media-Based Disaster Monitoring: A Review of NLP, Location Intelligence, and Multimodal Approaches

This review examined artificial intelligence-based approaches for disaster monitoring using social-media data. The reviewed studies demonstrate that combining natural language processing, disaster classification, location extraction, sentiment analysis, anomaly detection, and multimodal analysis can provide useful disaster intelligence [1], [6], [18], [21]. However, challenges such as noisy and multilingual data, geographical ambiguity, misinformation, and real-time processing remain. An integrated approach can therefore provide a broader representation of disaster-related information and support situational awareness during emergency events.

[1]  F. K. Sufi and I. Khalil, “Automated disaster monitoring from social media posts using AI-based location intelligence and sentiment analysis,” IEEE Transactions on Computational Social Systems, vol. 11, no. 4, pp. 4614–4624, 2024. [2]  C. Fan, F. Wu, and A. Mostafavi, “A hybrid machine learning pipeline for automated mapping of events and locations from social media in disasters,” IEEE Access, vol. 8, pp. 10478–10490, 2020. [3]  J. Yin, A. Lampert, M. Cameron, B. Robinson, and R. Power, “Using social media to enhance emergency situation awareness,” IEEE Intelligent Systems, vol. 27, no. 6, pp. 52–59, 2012. [4] U. A. Bukar, M. A. Jabar, F. Sidi, R. N. H. Nor, S. Abdullah, and M. Othman, “Crisis informatics in the context of social media crisis communication: Theoretical models, taxonomy, and open issues,” IEEE Access, vol. 8, pp. 185842–185869, 2020. [5]   F. A. Azlan, A. Ahmad, S. Yussof, and A. A. A. Ghapar, “Analyzing algorithms to detect disaster events using social media,” in Proc. 8th Int. Conf. Information Technology and Multimedia (ICIMU), 2020. [6]   A. F. Dahlan and C. Yuangyai, “T5-based named entity recognition for social media: A case study for location extraction,” in Proc. IEEE Int. Conf. Industry 4.0, Artificial Intelligence, and Communications Technology (IAICT), 2024. [7]   S. Soni, S. N. Gupta, R. Devi, and K. Hazra, “Information extraction from tweets for disaster damage assessment using rule-based NLP,” in Proc. 15th Int. Conf. Computing Communication and Networking Technologies (ICCCNT), 2024. [8]  A. Ridwan, H. H. Nuha, and R. Dharayani, “Sentiment analysis of floods on Twitter social media using the Naive Bayes classifier method with the N-Gram feature,” in Proc. Int. Conf. Data Science and Its Applications (ICoDSA), 2022. [9]  N. H. Khun, T. T. Zin, M. Yokota, and H. A. Thant, “Emotion analysis of Twitter users on natural disasters,” in Proc. IEEE 8th Global Conf. Consumer Electronics (GCCE), pp. 342–343, 2019. [10]  F. Alam, F. Ofli, M. Imran, T. Alam, and U. Qazi, “Deep learning benchmarks and datasets for social media image classification for disaster response,” in Proc. IEEE/ACM Int. Conf. Advances in Social Networks Analysis and Mining (ASONAM), pp. 151–158, 2020.