A Comparative Study of Deep Learning Methods for the Detection and Classification of Natural Disasters from Social Media

Spyros Fontalis, Alexandros Zamichos, Maria Tsourma, Anastasis Drosou, Dimitrios Tzovaras

2023

Abstract

Disaster Management, defined as a coordinated social effort to successfully prepare for and respond to disasters, can benefit greatly as an industrial process from modern Deep Learning methods. Disaster prevention organizations can benefit greatly from the processing of disaster response data. In an attempt to detect and subsequently categorise disaster-related information from tweets via tweet text analysis, a Feedforward Neural Network (FNN), a Convolutional Neural Network, a Bi-directional Long Short-Term Memory (BLSTM), as well as several Transformer-based network architectures, namely BERT, DistilBERT, Albert, RoBERTa and DeBERTa, are employed. The two defined main tasks of the work presented in this paper are: (1) distinguishing tweets into disaster related and non relevant ones, and (2) categorising already labeled disaster tweets into eight predefined natural disaster categories. These supported types of natural disasters are earthquakes, floods, hurricanes, wildfires, tornadoes, explosions, volcano eruptions and general disasters. To achieve this goal, several accessible related datasets are collected and combined to suit the two tasks. In addition, the combination of preprocessing tasks that is most beneficial for inference is investigated. Finally, experiments have been conducted using bias mitigation techniques.

Paper Citation

in Harvard Style

Fontalis S., Zamichos A., Tsourma M., Drosou A. and Tzovaras D. (2023). A Comparative Study of Deep Learning Methods for the Detection and Classification of Natural Disasters from Social Media. In Proceedings of the 12th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM, ISBN 978-989-758-626-2, SciTePress, pages 320-327. DOI: 10.5220/0011666500003411

in Bibtex Style

@conference{icpram23,
author={Spyros Fontalis and Alexandros Zamichos and Maria Tsourma and Anastasis Drosou and Dimitrios Tzovaras},
title={A Comparative Study of Deep Learning Methods for the Detection and Classification of Natural Disasters from Social Media},
booktitle={Proceedings of the 12th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM,},
year={2023},
pages={320-327},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0011666500003411},
isbn={978-989-758-626-2},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 12th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM,
TI - A Comparative Study of Deep Learning Methods for the Detection and Classification of Natural Disasters from Social Media
SN - 978-989-758-626-2
AU - Fontalis S.
AU - Zamichos A.
AU - Tsourma M.
AU - Drosou A.
AU - Tzovaras D.
PY - 2023
SP - 320
EP - 327
DO - 10.5220/0011666500003411
PB - SciTePress