Abstract
Natural calamities are ineluctable and have caused severe damage to both life and property. The rate of the occurrence of natural disasters has been drastically increasing over time. It takes a long time to abate the impact of these calamities. One such natural disaster, the flood has caused a severe impact on the lives of people. Chennai, the capital city of Tamil Nadu is frequently affected by floods due to heavy monsoon rains, especially in recent years. Under these difficult circumstances, social media platforms like Facebook and Twitter have played a veritably huge part in the communication of people. This paper proposes Deep Learning models and Natural Language Processing (NLP) models to classify social media posts and perform spatiotemporal modelling for finding the exact time and location of flood affected areas to examine the flood severity and take immediate recovery response. The proposed methodology, DistilBERT outperforms other traditional models as most of them are keyword based which limits the scope of the classification. To overcome the disadvantages faced by geotag based approaches, Named Entity Recognition (NER) is proposed to find the location. Both the models are trained using social media feeds posted during the Chennai floods. The accuracy obtained by the proposed methodology is 99% for text classification (DistilBERT) and 89% for location identification (NER). The results obtained imply that the proposed methodology can be an efficient approach for disaster management.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Hashim KF, Ishak SH, Ahmad M (2015) A study on social media application as a tool to share information during flood disaster. ARPN J Eng Appl Sci 10(3):959–967
Statista webpage, https://www.statista.com/statistics/242606/number-of-active-twitter-users-in-selected-countries/, last accessed 07 Jan 2022
Pourebrahim N, Sultana S, Edwards J, Gochanour A, Mohanty S (2019) Understanding communication dynamics on Twitter during natural disasters: a case study of Hurricane Sandy. Int J Disaster Risk Reduct 37:101176
Resch B, Usländer F, Havas C (2018) Combining machine-learning topic models and spatiotemporal analysis of social media data for disaster footprint and damage assessment. Cartogr Geogr Inf Sci 45(4):362–376
Sanh V, Debut L, Chaumond J, Wolf T (2019) DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter. arXiv preprint arXiv:1910.01108
Mohit B (2014) Named entity recognition. In: Natural language processing of semitic languages. Springer, Berlin, Heidelberg, pp. 221–245
Niles MT, Emery BF, Reagan AJ, Dodds PS, Danforth CM (2019) Social media usage patterns during natural hazards. PLoS ONE 14(2):e0210484
Robinson B, Power R, Cameron M (2013) A sensitive twitter earthquake detector. In: Proceedings of the 22nd international conference on world wide web, pp. 999–1002
De Albuquerque JP, Herfort B, Brenning A, Zipf A (2015) A geographic approach for combining social media and authoritative data towards identifying useful information for disaster management. Int J Geogr Inf Sci 29(4):667–689
Abirami S, Chitra P (2019) Real time twitter based disaster response system for indian scenarios. In: 2019 26th International Conference on High Performance Computing, Data and Analytics Workshop (HiPCW). IEEE, pp. 82–86
Goswami S, Raychaudhuri D (2020) Identification of disaster-related tweets using natural language processing: International Conference on Recent Trends in Artificial Intelligence, IOT, Smart Cities & Applications (ICAISC-2020). IOT, Smart Cities & Applications (ICAISC-2020), 26 May 2020
Zhang C, Zhou G, Yuan Q, Zhuang H, Zheng Y, Kaplan L, ... Han J (2016) Geoburst: Real-time local event detection in geo-tagged tweet streams. In: Proceedings of the 39th International ACM SIGIR conference on Research and Development in Information Retrieval, pp. 513–522
Hodas NO, Ver Steeg G, Harrison J, Chikkagoudar S, Bell E, Corley, CD (2015) Disentangling the lexicons of disaster response in twitter. In: Proceedings of the 24th International Conference on World Wide Web, pp. 1201–1204
Malik M, Lamba H, Nakos C, Pfeffer J (2015) Population bias in geotagged tweets. In: proceedings of the international AAAI conference on web and social media, vol. 9, No. 4, pp. 18–27
Kanth AK, Chitra P, Sowmya GG (2022) Deep learning-based assessment of flood severity using social media streams. Stochastic Environmental Research and Risk Assessment, 1–21
Twitter Developer Page, https://developer.twitter.com/en/docs, last accessed 01 May 2022
Devlin J, Chang MW, Lee K, Toutanova K (2018). Bert: Pre-training of deep bidirectional transformers for language understanding. ArXiv preprint arXiv:1810.04805
Hossin M, Sulaiman MN (2015) A review on evaluation metrics for data classification evaluations. Int J Data Min & Knowl Manag Process 5(2):1
Basu P, Roy TS, Naidu R, Muftuoglu Z, Singh S, Mireshghallah F (2021) Benchmarking differential privacy and federated learning for bert models. ArXiv preprint arXiv:2106.13973
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 Singapore Pte Ltd.
About this paper
Cite this paper
Gokul Raj, S., Chitra, P., Silesh, A., Lingeshwaran, R. (2023). Flood Severity Assessment Using DistilBERT and NER. In: Singh, P., Singh, D., Tiwari, V., Misra, S. (eds) Machine Learning and Computational Intelligence Techniques for Data Engineering. MISP 2022. Lecture Notes in Electrical Engineering, vol 998. Springer, Singapore. https://doi.org/10.1007/978-981-99-0047-3_34
Download citation
DOI: https://doi.org/10.1007/978-981-99-0047-3_34
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-99-0046-6
Online ISBN: 978-981-99-0047-3
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)