A comparison of word embedding-based extraction feature techniques and deep learning models of natural disaster messages classification

• Autorzy: Faisal Mohammad Reza , Budiman Irwan , Abadi Friska , Haekal Muhammad , Nugrahadi Dodon Turianto

Identyfikatory

DOI

10.35784/jcsi.3322

Warianty tytułu

PL

Porównanie technik wyodrębniania cech opartych na osadzeniu słów oraz modeli głębokiego uczenia w klasyfikacji wiadomości o klęskach żywiołowych

• Języki publikacji: EN

Abstrakty

EN

The research aims to compare the classification performance of natural disaster messages classification from Twitter. The research experiment covers the analysis of three-word embedding-based extraction feature techniques and five different models of deep learning. The word embedding techniques that are used in this experiment are Word2Vec, fastText, and Glove. The experiment uses five deep learning models, namely three models of different dimensions of Convolutional Neural Network (1D CNN, 2D CNN, 3D CNN), Long Short-Term Memory Network (LSTM), and Bidirectional Encoder Representations for Transformer (BERT). The models are tested on four natural disaster messages datasets: earthquakes, floods, forest fires, and hurricanes. Those models are tested for classification performance.

PL

Badanie ma na celu porównanie skuteczności klasyfikacji wiadomości o klęskach żywiołowych z Twittera. Eksperyment badawczy obejmuje analizę technik ekstrakcji cech opartych na osadzeniu trzech słów oraz pięciu różnych modeli głębokiego uczenia. Techniki osadzania słów używane w tym eksperymencie to Word2Vec, fastText i Glove. Eksperyment wykorzystuje pięć modeli głębokiego uczenia, a mianowicie trzy modele o różnych wymiarach konwolucyjnej sieci neuronowej (1D CNN, 2D CNN, 3D CNN), oraz dwie sieci: Long Short-Term Memory Network (LSTM) oraz Bidirectional Encoder Representations for Transformer (BERT). Modele zostały prztestowane na czterech zestawach danych dotyczących klęsk żywiołowych, a mianowicie trzęsień ziemi, powodzi, pożarów lasów i huraganów. Modele te przetestowano pod kątem wydajności klasyfikacji.

Słowa kluczowe

EN

Twitter; natural disaster; CNN; LSTM; BERT

PL

twitter; klęska żywiołowa; CNN; LSTM; BERT

• Wydawca: Wydawnictwo Politechniki Lubelskiej
• Czasopismo: Journal of Computer Sciences Institute
• Rocznik: 2023
• Tom: Vol. 27
• Strony: 145--153
• Opis fizyczny: Bibliogr. 27 poz., fig., tab.

Twórcy

autor

Faisal Mohammad Reza

• Lambung Mangkurat University (Indonesia)

autor

Budiman Irwan

• Lambung Mangkurat University (Indonesia)

autor

Abadi Friska

• Lambung Mangkurat University (Indonesia)

autor

Haekal Muhammad

• Lambung Mangkurat University (Indonesia)

autor

Nugrahadi Dodon Turianto

• Lambung Mangkurat University (Indonesia)

Bibliografia

• 1. D. Wu, Y. Cui, Disaster early warning and damage assessment analysis using social media data and geo-location information, Decision Support Systems 111 (2018) 48-59, https://doi.org/10.1016/j.dss.2018.04.005.DOI: https://doi.org/10.1016/j.dss.2018.04.005
• 2. K. M Rodriguez, S. K. Ofori, L. C. Bayliss, J. S. Schwind, K. Diallo, M. Liu, J. Yin, G. Chowell, I. C. H. Fung, Social media use in emergency response to natural disasters: a systematic review with a public health perspective, Disaster Medicine and Public Health Preparedness, 14(1) (2020) 139-149, https://doi.org/10.1017/dmp.2020.3.DOI: https://doi.org/10.1017/dmp.2020.3
• 3. K. Zahra, M. Imran, F. O. Ostermann, Automatic identification of eyewitness messages on twitter during disasters, Information Processing & Management, 57(1) (2020) 102-107, https://doi.org/10.1016/j.ipm.2019.102107.DOI: https://doi.org/10.1016/j.ipm.2019.102107
• 4. Devaraj, D. Murthy, A. Dontula, Machine learning methods for identifying social media-based requests for urgent help during hurricanes, International Journal of Disaster Risk Reduction 51 (2020) 101757, https://doi.org/10.1016/j.ijdrr.2020.101757.DOI: https://doi.org/10.1016/j.ijdrr.2020.101757
• 5. Jang, M. Kim, G. Harerimana, S. Kang, J. W. Kim, Bi-LSTM model to increase accuracy in text classification: Combining Word2vec CNN and attention mechanism, Applied Sciences 10(17) (2020) 5841, https://doi.org/10.3390/app10175841.DOI: https://doi.org/10.3390/app10175841
• 6. M. R. Faisal, R. A. Nugroho, R. Ramadhani, F. Abadi, R. Herteno, T. H. Saragih, Natural Disaster on Twitter: Role of Feature Extraction Method of Word2Vec and Lexicon Based for Determining Direct Eyewitness, Trends in Sciences 18(23) (2021) 680-680, https://doi.org/10.48048/tis.2021.680.DOI: https://doi.org/10.48048/tis.2021.680
• 7. R. Rinaldi, M. R. Faisal, M. I. Mazdadi, R. A. Nugroho, F. Abadi, Eye witness message identification on forest fires disaster using convolutional neural network, Journal of Data Science and Software Engineering 2(02) (2021) 100-108.
• 8. J. O. Luna, D. Ari, Word Embeddings and Deep Learning for Spanish Twitter Sentiment Analysis, Communications in Computer and Information Science vol 898 Springer (2019) 19-31, https://doi.org/10.1007/978-3-030-11680-4_4.DOI: https://doi.org/10.1007/978-3-030-11680-4_4
• 9. D. Li, J. Zhang, Q .Zhang, X. Wei, Classification of ECG signals based on 1D convolution neural network, IEEE 19th International Conference on e-Health Networking Applications and Services (Healthcom) (2017) 1-6, https://doi.org/10.1109/HealthCom.2017.8210784.DOI: https://doi.org/10.1109/HealthCom.2017.8210784
• 10. H.M. Rai, K. Chatterjee, 2D MRI image analysis and brain tumor detection using deep learning CNN model LeU-Net, Multimedia Tools and Applications 80 (2021) 36111–36141, https://doi.org/10.1007/s11042-021-11504-9.DOI: https://doi.org/10.1007/s11042-021-11504-9
• 11. B. Khagi, G. R. Kwon, 3D CNN design for the classification of Alzheimer’s disease using brain MRI and PET, IEEE Access 8 (2020) 217830-217847, https://doi.org/10.1109/ACCESS.2020.3040486.DOI: https://doi.org/10.1109/ACCESS.2020.3040486
• 12. Y. Goldberg, O. Levy, word2vec Explained: deriving Mikolov et al.'s negative-sampling word-embedding method, arXiv:1402.3722 (2014).
• 13. J. Pennington, R. Socher, C. D. Manning, Glove: Global vectors for word representation, In Proceedings of the 2014 conference on empirical methods in natural language processing (EMNLP) (2014) 1532-1543.DOI: https://doi.org/10.3115/v1/D14-1162
• 14. U. D. Gandhi, P. M. Kumar, G. C. Babu, G. Karthick, Sentiment Analysis on Twitter Data by Using Convolutional Neural Network (CNN) and Long Short Term Memory (LSTM), Wireless Personal Communications (2021) 1-10, https://doi.org/10.1007/s11277-021-08580-3.DOI: https://doi.org/10.1007/s11277-021-08580-3
• 15. Bhoi, S. P. Pujari, R. C. Balabantaray, A deep learning-based social media text analysis framework for disaster resource management, Social Network Analysis and Mining 10 78 (2020) 1-14, https://doi.org/10.1007/s13278-020-00692-1.DOI: https://doi.org/10.1007/s13278-020-00692-1
• 16. J. Devlin, M. W. Chang, K. Lee, K. Toutanova, Bert: Pre-training of deep bidirectional transformers for language understanding, arXiv:1810.04805 (2018).
• 17. S. G. Carvajal, E. C. G. Merchán, Comparing BERT against traditional machine learning text classification. arXiv:2005.13012 (2020).
• 18. W. Maharani, Sentiment analysis during Jakarta flood for emergency responses and situational awareness in disaster management using BERT, 8th International Conference on Information and Communication Technology (ICoICT) (2020) 1-5, https://doi.org/10.1109/ICoICT49345.2020.9166407.DOI: https://doi.org/10.1109/ICoICT49345.2020.9166407
• 19. M. K. Delimayanti, R. Sari, M. Laya, M. R. Faisal, R. F. Naryanto, The effect of pre-processing on the classification of twitter’s flood disaster messages using support vector machine algorithm, 3rd International Conference on Applied Engineering (ICAE) (2020) 1-6, https://doi.org/10.1109/ICAE50557.2020.9350387.DOI: https://doi.org/10.1109/ICAE50557.2020.9350387
• 20. S. Khomsah, R. D. Ramadhani, S. Wijaya, The Accuracy Comparison Between Word2Vec and FastText On Sentiment Analysis of Hotel Reviews, Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi) 6(3) (2022) 352-358, https://doi.org/10.29207/resti.v6i3.3711.DOI: https://doi.org/10.29207/resti.v6i3.3711
• 21. F. Anistya, E. B. Setiawan, Hate Speech Detection on Twitter in Indonesia with Feature Expansion Using GloVe, Jurnal RESTI (Rekayasa Sistem Dan Teknologi Informasi) 5(6) (2021) 1044-1051, https://doi.org/10.29207/resti.v5i6.3521.DOI: https://doi.org/10.29207/resti.v5i6.3521
• 22. R. Chauhan, K. K. Ghanshala, R. C. Joshi, Convolutional neural network (CNN) for image detection and recognition, 1st International Conference on Secure Cyber Computing and Communication (ICSCCC) (2018) 278-282, https://doi.org/10.1109/ICSCCC.2018.8703316.DOI: https://doi.org/10.1109/ICSCCC.2018.8703316
• 23. K. Dubey, V. Jain, Comparative Study of Convolution Neural Network’s Relu and Leaky-Relu Activation Functions, Applications of Computing, Automation and Wireless Systems in Electrical Engineering (2019) 873-880 https://doi.org/10.1007/978-981-13-6772-4_76.DOI: https://doi.org/10.1007/978-981-13-6772-4_76
• 24. S. S. Basha, S. R. Dubey, V. Pulabaigari, S. Mukherjee, Impact of fully connected layers on performance of convolutional neural networks for image classification, Neurocomputing 378 (2020) 112-119, https://doi.org/10.1016/j.neucom.2019.10.008.DOI: https://doi.org/10.1016/j.neucom.2019.10.008
• 25. S. Bodapati, H. Bandarupally, R.N. Shaw, A. Ghosh, Comparison and Analysis of RNN-LSTMs and CNNs for Social Reviews Classification, Advances in Applications of Data-Driven Computing (2021) 49-59, https://doi.org/10.1007/978-981-33-6919-1_4.DOI: https://doi.org/10.1007/978-981-33-6919-1_4
• 26. Y. Yu, X. Si, C. Hu, J. Zhang, A review of recurrent neural networks: LSTM cells and network architectures, Neural Computation 31(7) (2019) 1235-1270, https://doi.org/10.1162/neco_a_01199.DOI: https://doi.org/10.1162/neco_a_01199
• 27. J. Bissmark, O. Wärnling, The Sparse Data Problem Within Classification Algorithms : The Effect of Sparse Data on the Naïve Bayes Algorithm (Dissertation). (2017). Retrieved from http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-209227

Uwagi

Opracowanie rekordu ze środków MNiSW, umowa nr POPUL/SP/0154/2024/02 w ramach programu "Społeczna odpowiedzialność nauki II" - moduł: Popularyzacja nauki (2025).