FOREST FIRE LOCATION AND TIME RECOGNITION IN SOCIAL MEDIA TEXT USING XLM-ROBERTA
DOI:
https://doi.org/10.33480/jitk.v10i4.6194Keywords:
entity recognition, forest fire, social media text, xlm-robertaAbstract
Forest fires have become a serious global threat, significantly impacting ecosystems, communities, and economies. Although remote sensing technology shows potential, limitations such as time delays, limited sensor coverage, and low resolution reduce its effectiveness for real-time forest fire detection. Additionally, social media can serve as a multimodal sensor, presenting multilingual text data with rapid and global coverage. However, it may encounter challenges in obtaining location and time information on forest fires due to limitations in datasets and model generalization. This study aims to develop a multilingual named entity recognition (NER) model to identify location and time entities of forest fires in social media texts such as tweets. Utilizing a transfer learning approach with the XLM-RoBERTa architecture, fine-tuning was performed using the general-purpose Nergrit corpus dataset containing 19 entities, which were relabeled into 3 main entities to detect location, date, and time entities from tweets. This approach significantly improves the model's ability to generalize to disaster domains across multiple languages and noisy social media texts. With a fine-tuning accuracy of 98.58% and a maximum validation accuracy of 96.50%, the model offers a novel capability for disaster management agencies to detect forest fires in a scalable, globally inclusive manner, enhancing disaster response and mitigation efforts.
Downloads
References
A. Tyukavina et al., “Global Trends of Forest Loss Due to Fire From 2001 to 2019,” Frontiers in Remote Sensing, vol. 3, 2022, doi: 10.3389/frsen.2022.825190.
A. Setyanto et al., “Ecological Impact Assessment Framework for Areas Affected by Natural Disasters,” in Proceedings of the 19th International Conference on Content-Based Multimedia Indexing, in CBMI ’22. New York, NY, USA: Association for Computing Machinery, 2022, pp. 155–161. doi: 10.1145/3549555.3549596.
M. Weisse, L. Goldman, and S. Carter, “Tropical Forest Loss Drops Steeply in Brazil and Colombia, but High Rates Persist Overall,” Apr. 2024. [Online]. Available: https://research.wri.org/gfr/latest-analysis-deforestation-trends
Z. Zheng et al., “Wildfire Detection Based on the Spatiotemporal and Spectral Features of Himawari-8 Data,” IEEE Transactions on Geoscience and Remote Sensing, 2024.
K. A. Yuana et al., “GIS data support technique for forest fire management and decision support system: A Sebangau National Park, Kalimantan case,” in 2023 6th International Conference on Information and Communications Technology (ICOIACT), 2023, pp. 286–291. doi: 10.1109/ICOIACT59844.2023.10455935.
J. Zulkarnain, M. R. Pahlevi, Y. Astica, W. Pangestuti, and Kusrini, “Fire Detection based on Smoke Image using Convolutional Neural Network (CNN),” in 2022 4th International Conference on Cybernetics and Intelligent System (ICORIS), 2022, pp. 1–5. doi: 10.1109/ICORIS56080.2022.10031410.
A. D. Laksito et al., “Machine Learning and Social Media Harvesting for Wildfire Prevention,” in 2023 IEEE 13th International Conference on Pattern Recognition Systems (ICPRS), 2023, pp. 1–6. doi: 10.1109/ICPRS58416.2023.10179001.
J. Phengsuwan et al., “Use of Social Media Data in Disaster Management: A Survey,” Future Internet, vol. 13, no. 2, 2021, doi: 10.3390/fi13020046.
X. X. Zhu et al., “Geoinformation harvesting from social media data: A community remote sensing approach,” IEEE Geosci Remote Sens Mag, vol. 10, no. 4, pp. 150–180, 2023.
L. Li, Z. Ma, and T. Cao, “Data-driven investigations of using social media to aid evacuations amid Western United States wildfire season,” Fire Saf J, vol. 126, p. 103480, Dec. 2021, doi: 10.1016/J.FIRESAF.2021.103480.
J. Phengsuwan et al., “Use of social media data in disaster management: a survey,” Future Internet, vol. 13, no. 2, p. 46, 2021.
S. A. Shah, S. Ben Yahia, K. McBride, A. Jamil, and D. Draheim, “Twitter Streaming Data Analytics for Disaster Alerts,” in 2021 2nd International Informatics and Software Engineering Conference (IISEC), 2021, pp. 1–6. doi: 10.1109/IISEC54230.2021.9672370.
H. Sanjaya, K. Kusrini, K. A. Yuana, and J. R. M. Salio, “Multilingual Named Entity Recognition Model for Location and Time Extraction of Forest Fire,” in 2024 4th International Conference of Science and Information Technology in Smart Administration (ICSINTESA), 2024, pp. 611–615. doi: 10.1109/ICSINTESA62455.2024.10747844.
E. H. Muktafin and P. Kusrini, “Sentiments analysis of customer satisfaction in public services using K-nearest neighbors algorithm and natural language processing approach,” TELKOMNIKA (Telecommunication Computing Electronics and Control), vol. 19, no. 1, pp. 146–154, Feb. 2021, doi: 10.12928/TELKOMNIKA.V19I1.17417.
A. Deshpande, P. Talukdar, and K. Narasimhan, “When is BERT multilingual? isolating crucial ingredients for cross-lingual transfer,” arXiv preprint arXiv:2110.14782, 2021.
R. Koshy and S. Elango, “Applying social media in emergency response: an attention-based bidirectional deep learning system for location reference recognition in disaster tweets,” Applied Intelligence, 2024, doi: 10.1007/s10489-024-05462-6.
N. Eligüzel, C. Çetinkaya, and T. Dereli, “Application of named entity recognition on tweets during earthquake disaster: a deep learning-based approach,” Soft comput, vol. 26, no. 1, pp. 395–421, 2022, doi: 10.1007/s00500-021-06370-4.
R. Suwaileh, T. Elsayed, M. Imran, and H. Sajjad, “When a disaster happens, we are ready: Location mention recognition from crisis tweets,” International Journal of Disaster Risk Reduction, vol. 78, p. 103107, Aug. 2022, doi: 10.1016/J.IJDRR.2022.103107.
C. Berragan, A. Singleton, A. Calafiore, and J. Morley, “Transformer based named entity recognition for place name extraction from unstructured text,” International Journal of Geographical Information Science, vol. 37, no. 4, pp. 747–766, 2023, doi: 10.1080/13658816.2022.2133125.
D. Rothman, Transformers for Natural Language Processing: Build, train, and fine-tune deep neural network architectures for NLP with Python, Hugging Face, and OpenAI’s GPT-3, ChatGPT, and GPT-4. Packt Publishing Ltd, 2022.
S. Akpatsa et al., “Online news sentiment classification using distilbert,” Journal of Quantum Computing, vol. 4, no. 1, p. 1, 2022.
K. L. Tan, C. P. Lee, K. S. M. Anbananthen, and K. M. Lim, “RoBERTa-LSTM: a hybrid model for sentiment analysis with transformer and recurrent neural network,” IEEE Access, vol. 10, pp. 21517–21525, 2022.
N. Deng, H. Fu, and X. Chen, “Named Entity Recognition of Traditional Chinese Medicine Patents Based on BiLSTM-CRF,” Wirel Commun Mob Comput, vol. 2021, no. 1, p. 6696205, 2021.
G. Girsang and B. Noveta, “Six classes named entity recognition for mapping location of Indonesia natural disasters from twitter data,” International Journal of Intelligent Computing and Cybernetics, May 2024, doi: 10.1108/IJICC-09-2023-0251.
PT Gria Inovasi Teknologi, “Nergrit Corpus,” Huggingface. Accessed: Jan. 15, 2024. [Online]. Available: https://huggingface.co/datasets/id_nergrit_corpus
A. Gaikwad, P. Belhekar, and V. Kottawar, “Advancing Multilingual Sentiment Understanding with XGBoost, SVM, and XLM-RoBERTa,” in International Conference on Data Science, Machine Learning and Applications, 2023, pp. 990–1000.
P. Azunre, Transfer Learning for Natural Language Processing. Manning, 2021. [Online]. Available: https://books.google.co.id/books?id=bGI7EAAAQBAJ
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2025 Hafidz Sanjaya, Kusrini Kusrini, Kumara Ari Yuana, Arief Setyanto, I Made Artha Agastya, Simone Martin Marotta, José Ramón Martínez Salio
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
-a.jpg)
-b.jpg)
