Abstract
Recent developments in Natural Language Processing (NLP) have opened up a plethora of opportunities to extract pertinent information in settings where data overload is a critical issue. In this work, we address the highly relevant scenario of fire detection and deployment of firefighting resources. Social media posts commonly contain textual information during a fire event, but their vast volume and the necessity for swift actionable information often precludes their effective utilization. This paper proposes an information extraction pipeline capable of generating a wildfire heat map of Portugal from Twitter posts written in Portuguese. It uses a fine-tuned version of a BERT language model to extract fire reports from large batches of recent fire-related tweets as well as the spaCy NLP library to query the location of each recently reported fire. Wildfire locations are plotted to a colored map indicating the most probable fire locations, which could prove useful in the process of allocating firefighting resources for those regions. The system is easily adaptable to work with any other country or language, provided compatible BERT and spaCy models exist.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
https://www.epa.gov/climate-indicators/climate-change-indicators-wildfires (accessed 2023-07-23).
- 2.
https://github.com/cabralpinto/wildfire-heat-map-generation (accessed 2023-07-23).
- 3.
https://www.bestproxyreviews.com/twitter-statistics (accessed 2023-07-23).
- 4.
https://github.com/JustAnotherArchivist/snscrape (accessed 2023-07-23).
- 5.
https://nominatim.org/release-docs/latest/api/Overview (accessed 2023-07-23).
- 6.
https://fireloc.org/?lang=en (accessed 2023-07-23).
- 7.
For further details, see https://scikit-learn.org/stable/modules/generated/sklearn.model_selection.StratifiedShuffleSplit.html.
References
Altowaijri, A.H., Alfaifi, M.S., Alshawi, T.A., Ibrahim, A.B., Alshebeili, S.A.: A privacy-preserving IoT-based fire detector. IEEE Access 9, 51393–51402 (2021). https://doi.org/10.1109/ACCESS.2021.3069588
Boulton, C.A., Shotton, H., Williams, H.T.P.: Using social media to detect and locate wildfires. In: Proceedings of the International AAAI Conference on Web and Social Media (2016)
Deb, S., Chanda, A.K.: Comparative analysis of contextual and context-free embeddings in disaster prediction from Twitter data. Mach. Learn. Appl. 7, 100253 (2022). https://doi.org/10.1016/j.mlwa.2022.100253. https://www.sciencedirect.com/science/article/pii/S2666827022000032
Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: BERT: pre-training of deep bidirectional transformers for language understanding. In: Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long and Short Papers), Minneapolis, Minnesota, pp. 4171–4186. Association for Computational Linguistics (2019). https://doi.org/10.18653/v1/N19-1423. https://aclanthology.org/N19-1423
Muhammad, K., Ahmad, J., Mehmood, I., Rho, S., Baik, S.W.: Convolutional neural networks based fire detection in surveillance videos. IEEE Access 6, 18174–18183 (2018). https://doi.org/10.1109/ACCESS.2018.2812835
Phelps, N., Woolford, D.G.: Comparing calibrated statistical and machine learning methods for wildland fire occurrence prediction: a case study of human-caused fires. Int. J. Wildland Fire 30, 850–870 (2021). https://doi.org/10.1071/WF20139
Radford, A., Narasimhan, K., Salimans, T., Sutskever, I.: Improving language understanding by generative pre-training (2018)
Saponara, S., Elhanashi, A., Gagliardi, A.: Real-time video fire/smoke detection based on CNN in antifire surveillance systems. J. Real-Time Image Proc. 18(3), 889–900 (2020). https://doi.org/10.1007/s11554-020-01044-0
Silva, C., Cardoso, A., Ribeiro, B.: Crowdsourcing holistic deep approach for fire identification. In: IX International Conference on Forest Fire Research (2022)
Souza, F., Nogueira, R., Lotufo, R.: BERTimbau: pretrained BERT models for Brazilian Portuguese. In: Cerri, R., Prati, R.C. (eds.) BRACIS 2020. LNCS (LNAI), vol. 12319, pp. 403–417. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-61377-8_28
Thanos, K.G., Polydouri, A., Danelakis, A., Kyriazanos, D., Thomopoulos, S.C.: Combined deep learning and traditional NLP approaches for fire burst detection based on Twitter posts. In: Abu-Taieh, E., Mouatasim, A.E., Hadid, I.H.A. (eds.) Cyberspace, chap. 6. IntechOpen, Rijeka (2019). https://doi.org/10.5772/intechopen.85075
Töreyin, B.U., Dedeoğlu, Y., Güdükbay, U., çetin, A.E.: Computer vision based method for real-time fire and flame detection. Pattern Recogn. Lett. 27(1), 49–58 (2006). https://doi.org/10.1016/j.patrec.2005.06.015. https://www.sciencedirect.com/science/article/pii/S0167865505001819
Vaswani, A., et al.: Attention is all you need. In: Guyon, I., et al. (eds.) Advances in Neural Information Processing Systems, vol. 30. Curran Associates, Inc. (2017). https://proceedings.neurips.cc/paper/2017/file/3f5ee243547dee91fbd053c1c4a845aa-Paper.pdf
Vieweg, S., Hughes, A.L., Starbird, K., Palen, L.: Microblogging during two natural hazards events: what twitter may contribute to situational awareness. In: Proceedings of the SIGCHI Conference on Human Factors in Computing Systems (2010)
Zanca, D., Melacci, S., Gori, M.: Toward improving the evaluation of visual attention models: a crowdsourcing approach. In: 2020 International Joint Conference on Neural Networks, IJCNN 2020, Glasgow, United Kingdom, 19–24 July 2020, pp. 1–8. IEEE (2020). https://doi.org/10.1109/IJCNN48605.2020.9207438
Acknowledgments
This work is funded by the FCT – Foundation for Science and Technology, I.P./MCTES through national funds (PIDDAC), within the scope of CISUC R &D Unit - UIDB/00326/2020 or project code UIDP/00326/2020. This work is also funded by project FireLoc, supported by the Portuguese Foundation for Science and Technology (Fundação para a Ciência e a Tecnologia – FCT) under project grants PCIF/MPG/0128/2017.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Pinto, J.C., Gonçalo Oliveira, H., Cardoso, A., Silva, C. (2023). Generating Wildfire Heat Maps with Twitter and BERT. In: Quaresma, P., Camacho, D., Yin, H., Gonçalves, T., Julian, V., Tallón-Ballesteros, A.J. (eds) Intelligent Data Engineering and Automated Learning – IDEAL 2023. IDEAL 2023. Lecture Notes in Computer Science, vol 14404. Springer, Cham. https://doi.org/10.1007/978-3-031-48232-8_9
Download citation
DOI: https://doi.org/10.1007/978-3-031-48232-8_9
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-48231-1
Online ISBN: 978-3-031-48232-8
eBook Packages: Computer ScienceComputer Science (R0)