A Multi-Model Approach for Disaster-Related Tweets
A Comparative Study of Machine Learning and Neural Network Models
DOI:
https://doi.org/10.57159/gadl.jcmm.3.2.240125Keywords:
Disaster Tweets, Disaster Management, Machine Learning, Neural Networks, Natural Language ProcessingAbstract
This research centers around utilizing Natural Language Processing (NLP) techniques to analyze disaster-related tweets. The rising impact of global temperature shifts, leading to irregular weather patterns and increased water levels, has amplified the susceptibility to natural disasters. NLP offers a method for quickly identifying tweets about disasters, extracting crucial information, and identifying the types, locations, intensities, and effects of each type of disaster. This study uses a range of machine learning and neural network models and does a thorough comparison analysis to determine the best effective method for catastrophe recognition. Three well-known techniques, in-cluding the Multinomial Naive Bayes Classifier, the Passive Aggressive Classi-fier, and BERT (Bidirectional Encoder Representations from Transformers) were carefully examined with the ultimate goal of discovering the best strategy for correctly recognising disasters within the context of tweets. Among the three models, BERT achieved the highest performance in analyzing disaster-related tweets with an accuracy of 94.75%.
References
S. Goswami and D. Raychaudhuri, “Identification of disaster-related tweets using natural language processing,” in International Conference on Recent Trends in Artificial Intelligence, IoT, Smart Cities & Applications (ICAISC-2020), May 26, 2020.
A. Sharma, K. Thakur, D. S. Kapoor, K. J. Singh, T. Saroch, R. Kumar, S. Kumar, H. Sharma, K. Balachandran, J. H. Kim, and J. C. Bansal, “Disaster analysis through tweets,” in Third Congress on Intelligent Systems. CIS 2022. Lecture Notes in Networks and Systems (S. Kumar, H. Sharma, K. Balachandran, J. H. Kim, and J. C. Bansal, eds.), p. 608, Springer, Singapore, 2023.
H. Shekhar and S. Gangisetty, “Disaster analysis through tweets,” in Proceedings of the 2015 International Conference on Advanced Computing and Communication Technologies (ICACCT), IEEE, 2015.
R. Lamsal and T. Kumar, “Twitter-based disaster response using machine learning,” International Journal of Social Ecology and Sustainable Development, vol. 14, no. 1, pp. 1–18, 2023.
K. Chouhan, M. Yadav, R. Rout, K. Sahoo, N. Jhan-jhi, M. Masud, and S. Aljahdali, “Sentiment analysis with tweets behavior in Twitter streaming API,” Computer Systems Science and Engineering, vol. 45, 2022.
K. Ezukwoke and S. Zareian, “Online learning and active learning: A comparative study of passive-aggressive algorithm with support vector machine (SVM),” arXiv preprint arXiv:1909.09123, 2019.
Y. Liu, W. Li, and Y. Gao, “Passive-aggressive learning with feature evolvable streams,” Jisuanji Yanjiu yu Fazhan/Computer Research and Development, vol. 58, pp. 1575–1585, 2021.
D. H. Pham, “Exploring the effect of word embeddings and bag-of-words for Vietnamese sentiment analysis,” in Proceedings of the 2022 International Conference on Intelligent Systems and Applications (ISA), Springer, 2022.
V. Balakrishnan, Z. Shi, C. Law, R. Lim, L. Teh, Y. Fan, and J. Periasamy, “A comprehensive analysis of transformer-deep neural network models in Twitter disaster detection,” Mathematics, vol. 10, no. 2, p. 4664, 2022.
N. C. Dang, M. N. Moreno-García, and F. De la Prieta, “Sentiment analysis based on deep learning: A comparative study,” Electronics, vol. 9, no. 3, p. 483, 2020.
S. Deb and A. K. Chanda, “Comparative analysis of contextual and context-free embeddings in disaster prediction from Twitter data,” Machine Learning with Applications, vol. 7, p. 100253, 2022.
D. Prasad, A. Udeme, S. Misra, and H. Bisallah, “Identification and classification of transportation disaster tweets using improved bidirectional encoder representations from transformers,” International Journal of Information Management Data Insights, vol. 3, p. 100154, 2023.
G. Song and D. Huang, “A sentiment-aware contextual model for real-time disaster prediction using Twitter data,” Future Internet, vol. 13, no. 7, p. 163, 2021.
J. Lu, “Gradient descent, stochastic optimization, and other tales,” arXiv preprint arXiv:2205.00832, 2022.
S. N. Rai and A. Kumar, “BERT for disaster response: A systematic review,” Big Data and Cognitive Computing, vol. 6, no. 1, pp. 1–17, 2022.
A. Ningsih and A. Id Hadiana, “Disaster tweets classification in disaster response using bidirectional encoder representations from transformer (BERT),” in IOP Conference Series: Materials Science and Engineering, vol. 1115, p. 012032, 2021.
A. Ranade, S. Telge, and Y. Mate, “Predicting disasters from tweets using GloVe embeddings and BERT layer classification,” in Proceedings of the 2022 International Conference on Intelligent Systems and Applications (ISA), Springer, 2022.
A. D. Le, “Disaster tweets classification using BERT-based language model,” arXiv preprint arXiv:2202.00795, 2022.
J. Bochenek, J. Larson, S. Yao, and Y. Yang, “BERT for identifying disasters from tweets.” https://medium.com/analytics-vidhya/bert-for-identifying-disasters-from-tweets-50eeb6844302. Accessed: 2024-07-10.
J. V, G. H, Harikrishna, and P. H, “Disaster tweet classification using machine learning model,” in Proceedings of the 2023 4th International Conference on Smart Electronics and Communication (ICOSEC), IEEE, 2023.
W. Maharani, “Sentiment analysis during Jakarta flood for emergency responses and situational awareness in disaster management using BERT,” in Proceedings of the 2020 8th International Conference on Information and Communication Technology (ICoICT), IEEE, 2020.
Downloads
Published
How to Cite
License
Copyright (c) 2024 Journal of Computers, Mechanical and Management
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
The Journal of Computers, Mechanical and Management applies the CC Attribution- Non-Commercial 4.0 International License to its published articles. While retaining copyright ownership of the content, the journal permits activities such as downloading, reusing, reprinting, modifying, distributing, and copying of the articles, as long as the original authors and source are appropriately cited. Proper attribution is ensured by citing the original publication.
Accepted 2024-06-25
Published 2024-07-01
The journal is licensed under an 