An integrated deep CNN–LSTM framework for disaster management through reliable information retrieval and educational awareness
DOI:
https://doi.org/10.64268/inspire.v2i1.116Keywords:
Deep Learning, Disaster Management, Educational Awareness, Information Retrieval, Long Short-Term Memory (LSTM), Social MediaAbstract
Background: Social media has become one of the primary sources of disaster-related information; however, the rapid dissemination of heterogeneous, duplicated, and misleading content presents significant challenges for retrieving reliable information that can support disaster management and educational awareness. Conventional machine learning approaches often struggle to simultaneously capture semantic representations and contextual dependencies within large-scale disaster communications.
Aims: This study aims to develop and evaluate an integrated Deep CNN–LSTM-based disaster management framework for retrieving reliable disaster-related information from heterogeneous online sources while supporting educational awareness through safe information dissemination.
Methods: A quantitative experimental design was employed using disaster-related textual datasets collected from multiple online platforms, including earthquake, flood, wildfire, and COVID-19 events. The proposed framework integrated Deep Convolutional Neural Networks (Deep CNN) for semantic feature extraction with Long Short-Term Memory (LSTM) networks for sequential contextual learning. Model performance was compared with six benchmark machine learning and deep learning approaches, namely Support Vector Machine (SVM), Neural Network (NN), Feed-forward Neural Network (FFNN), Recurrent Neural Network (RNN), LSTM, and Hybrid CNN–LSTM. The framework was evaluated using retrieval performance together with Root Mean Square Error (RMSE), Mean Absolute Error (MAE), and the coefficient of determination (R²).
Result: The proposed framework consistently retrieved a greater amount of relevant disaster-related information across multiple disaster scenarios than the benchmark models. Quantitative evaluation further demonstrated robust predictive capability, achieving an RMSE of 15,286.2154, an MAE of 13,789.75, and the highest coefficient of determination (R² = 0.9793), indicating strong model fitting and reliable predictive performance.
Conclusion: The integrated Deep CNN–LSTM framework effectively combines semantic feature extraction and contextual sequence learning to improve disaster information retrieval from heterogeneous online sources. The proposed framework contributes to intelligent disaster management by providing reliable disaster-related information that supports educational awareness and evidence-based decision-making during disaster preparedness and emergency response.
References
Abdalla, R., & Ali, M. E. A. E.-F. (2019). WebGIS for disaster management and emergency response. Springer Nature. https://doi.org/10.1007/978-3-030-03828-1
Bouzidi, Z. (2022). Social networks for disaster management (Doctoral dissertation, University of Bouira, Algeria).
Bouzidi, Z. (2022, October 27–28). Améliorations dans le commerce et les affaires, la prévision des séries chronologiques financières, la détection des fraudes et le marketing grâce à l'apprentissage en profondeur, au Big Data et au supercalcul, tout en se méfiant des fausses nouvelles : Défi. Proceedings of the 2nd Conference of the Scientific Francophonie, University Agency of Francophonie, Cairo, Egypt.
Bouzidi, Z., Amad, M., & Boudries, A. (2019). Intelligent and real-time alert model for disaster management based on information retrieval from multiple sources. International Journal of Advanced Media and Communication, 7(4), 309–330. https://doi.org/10.1504/IJAMC.2019.111193
Bouzidi, Z., Amad, M., & Boudries, A. (2020). Deep learning-based automated learning environment using smart data to improve corporate marketing, business strategies, fraud detection in financial services, and financial time series forecasting. In Proceedings of the International Conference on Managing Business Through Web Analytics (ICMBWA 2020). Khemis Miliana University, Algeria.
Bouzidi, Z., Amad, M., & Boudries, A. (2022). Deep learning-based automated learning environment using smart data to improve corporate marketing, business strategies, fraud detection in financial services, and financial time series forecasting. In A. Sedkaoui (Ed.), Artificial intelligence and smart technologies for business applications. Springer.
Bouzidi, Z., & Boudries, A. (2025). Managing emergency crises using secure information through educational awareness: COVID-19 case study. Computers in Biology and Medicine, 186, Article 109620. https://doi.org/10.1016/j.compbiomed.2024.109620
Bouzidi, Z., Boudries, A., & Amad, M. (2020). Towards a smart interface-based automated learning environment through social media for disaster management and smart disaster education. In Proceedings of the Science and Information Conference (SAI 2020) (Vol. 1228, pp. 443–468). Springer. https://doi.org/10.1007/978-3-030-52249-0_31
Bouzidi, Z., Boudries, A., & Amad, M. (2021a). Deep learning and social media for managing disaster: Survey. In K. Arai (Ed.), Intelligent systems and applications (Lecture Notes in Networks and Systems, Vol. 294, pp. 12–30). Springer. https://doi.org/10.1007/978-3-030-82193-7_2
Bouzidi, Z., Boudries, A., & Amad, M. (2021b). Deep LSTM-based automated learning environment using smart data to improve awareness and education in time series forecasting. MC Medical Sciences, 1(5).
Bouzidi, Z., Boudries, A., & Amad, M. (2021c). LSTM-based automated learning with smart data to improve marketing fraud detection and financial forecasting. In Proceedings of the 5th International Scientific Conference on Economics and Management (EMAN 2021), Serbia.
Bouzidi, Z., Boudries, A., & Amad, M. (2022b). Smart education with deep learning and social media for disaster management in the pursuit of environmental sustainability while avoiding fake news. Research Square (Preprint). https://doi.org/10.21203/rs.3.rs-2042061/v1
Bouzidi, Z., Boudries, A., & Amad, M. (2022c). Context-based detecting fake news. Research Square (Preprint). https://doi.org/10.21203/rs.3.rs-2194376/v1
Clerveaux, V., Spence, B., & Katada, T. (2010). Promoting disaster awareness in multicultural societies: The DAG approach. Disaster Prevention and Management, 19(2), 199–218. https://doi.org/10.1108/09653561011038002
de Albuquerque, J. P., Herfort, B., Brenning, A., & Zipf, A. (2015). A geographic approach for combining social media and authoritative data towards identifying useful information for disaster management. International Journal of Geographical Information Science, 29(4), 667–689. https://doi.org/10.1080/13658816.2014.996567
Dussart, A., Pinel-Sauvagnat, K., & Hubert, G. (2020). Capitalizing on a TREC track to build a tweet summarization dataset. In Proceedings of the Text REtrieval Conference (TREC 2020).
He, R., Liu, Y., Yu, G., Tang, J., Hu, Q., & Dang, J. (2017). Twitter summarization with social-temporal context. World Wide Web, 20(2), 267–290. https://doi.org/10.1007/s11280-016-0386-0
Imran, M., Ofli, F., Caragea, D., & Torralba, A. (2020). Using AI and social media multimodal content for disaster response and management: Opportunities, challenges, and future directions. Information Processing & Management, 57(5), Article 102261. https://doi.org/10.1016/j.ipm.2020.102261
Kobayashi, K., Narita, A., Hirano, M., Tanaka, K., Katada, T., & Kuwasawa, K. (2008). DIGTable: A tabletop simulation system for disaster education. In Proceedings of the 6th International Conference on Pervasive Computing (pp. 57–60).
Kryvasheyeu, Y., Chen, H., Obradovich, N., Moro, E., Van Hentenryck, P., Fowler, J., & Cebrian, M. (2016). Rapid assessment of disaster damage using social media activity. Science Advances, 2(3), e1500779. https://doi.org/10.1126/sciadv.1500779
Lamsal, R., & Kumar, T. V. V. (2020). Classifying emergency tweets for disaster response. International Journal of Disaster Response and Emergency Management, 3(1), 14–29. https://doi.org/10.4018/IJDREM.2020010102
Li, L., Zhang, Q., Wang, X., Zhang, J., Wang, T., Gao, T.-L., Duan, W., Tan, K. K.-F., & Wang, F.-Y. (2020). Characterizing the propagation of situational information in social media during the COVID-19 epidemic: A case study on Weibo. IEEE Transactions on Computational Social Systems, 7(2), 556–562. https://doi.org/10.1109/TCSS.2020.2980007
Lin, C. K., Nifa, F. A. A., Musa, S., Shahron, S. A., & Anuar, N. A. (2018). Challenges and opportunities of disaster education programs among UUM students. In Proceedings of the 3rd International Conference on Applied Science and Technology (ICAST 2018). https://doi.org/10.1063/1.5055440
Misra, S., Sarkar, S., & Chatterjee, S. (2019). Sensors, cloud, and fog: The enabling technologies for the Internet of Things. CRC Press. https://doi.org/10.1201/9780429293986
Mitsuhara, H., Iwaka, K., Kozuki, Y., Shishibori, M., Inoue, T., Yamaguchi, K., Takechi, Y., & Morimoto, M. (2016). Penumbral tourism: Place-based disaster education via real-world disaster simulation. In Proceedings of the 3rd International Conference on Information and Communication Technologies for Disaster Management (ICT-DM 2016). IEEE.
Muttarak, R., & Lutz, W. (2014). Is education a key to reducing vulnerability to natural disasters and hence unavoidable climate change? Ecology and Society, 19(1), Article 42. https://doi.org/10.5751/ES-06476-190142
Nguyen, D. T., Al-Mannai, K., Joty, S. R., Sajjad, H., Imran, M., & Mitra, P. (2017). Robust classification of crisis-related data on social networks using convolutional neural networks. In Proceedings of the 11th International AAAI Conference on Web and Social Media (ICWSM 2017) (pp. 632–635).
Nurkartika Pascapurnama, D., Murakami, A., Chagan-Yasutan, H., Hattori, T., Sasaki, H., & Egawa, S. (2018). Integrated health education in disaster risk reduction: Lessons learned from disease outbreaks following natural disasters in Indonesia. International Journal of Disaster Risk Reduction, 29, 94–102. https://doi.org/10.1016/j.ijdrr.2017.07.013
Olteanu, A., Vieweg, S., & Castillo, C. (2015). What to expect when the unexpected happens: Social media communications across crises. In Proceedings of the 18th ACM Conference on Computer Supported Cooperative Work & Social Computing (pp. 994–1009). https://doi.org/10.1145/2675133.2675242
Qazi, A., Qazi, J., Naseer, K., Zeeshan, M., Hardaker, G., Maitama, J., & Haruna, K. (2020). Analyzing situational awareness through public opinion to predict adoption of social distancing amid the COVID-19 pandemic. Journal of Medical Virology, 92(7), 849–855. https://doi.org/10.1002/jmv.25840
Radford, A., Kim, J. W., Hallacy, C., Ramesh, A., Goh, G., Agarwal, S., Sastry, G., Askell, A., Mishkin, P., Clark, J., Krueger, G., & Sutskever, I. (2021). Learning transferable visual models from natural language supervision. In Proceedings of the 38th International Conference on Machine Learning (ICML 2021) (pp. 8748–8763). PMLR. https://doi.org/10.48550/arXiv.2103.00020
Rudra, K., Sharma, A., Ganguly, N., & Ghosh, S. (2018). Characterizing and countering communal microblogs during disaster events. IEEE Transactions on Computational Social Systems, 5(2), 403–417. https://doi.org/10.1109/TCSS.2017.2783222
Smith, S., & Ericson, E. (2019). Using immersive game-based virtual reality to teach fire-safety skills to children. Virtual Reality, 23(2), 87–99.
Torani, S., Majd, P. M., Maroufi, S. S., Dowlati, M., & Sheikhi, R. A. (2019). The importance of education on disasters and emergencies: A review article. Journal of Education and Health Promotion, 8, Article 85. https://doi.org/10.4103/jehp.jehp_262_18
Tsai, M. H., Chang, Y. L., Kao, C., & Kang, S. C. (2015). The effectiveness of a flood protection computer game for disaster education. Visualization in Engineering, 3(1), Article 9. https://doi.org/10.1186/s40327-015-0021-5
Vivakaran, M. V., & Neelamalar, M. (2018). Utilization of social media platforms for educational purposes among faculty in higher education: Evidence from Tamil Nadu. Higher Education for the Future, 5(1), 4–19. https://doi.org/10.1177/2347631117738638
Vulić, I., & Moens, M.-F. (2015). Monolingual and cross-lingual information retrieval models based on (bilingual) word embeddings. In Proceedings of the 38th International ACM SIGIR Conference on Research and Development in Information Retrieval (pp. 363–372). https://doi.org/10.1145/2766462.2767752
Wang, Z., & Ye, X. (2018). Social media analytics for natural disaster management. International Journal of Geographical Information Science, 32(1), 49–72. https://doi.org/10.1080/13658816.2017.1367003
Yu, Z., Sun, T., Sun, H., & Yang, F. (2015). Research on combinational forecast models for traffic flow. Mathematical Problems in Engineering, 2015, Article 567235. https://doi.org/10.1155/2015/567235
Zaini, N. A., Noor, S. F. M., & Zailani, S. Z. M. (2020). Design and development of a flood disaster game-based learning application based on learning domains. International Journal of Engineering and Advanced Technology, 9(4), 679–685. https://doi.org/10.35940/ijeat.C6216.049420
Zhao, X., Poria, S., Li, X., Chen, Y., & Tang, B. (2024). Toward robust multimodal learning using multimodal foundational models. arXiv. https://doi.org/10.48550/arXiv.2401.13697
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Zair Bouzidi
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
