No Cover Image

Journal article 360 views 45 downloads

Multi-Channel Convolutional Neural Network for the Identification of Eyewitness Tweets of Disaster

Abhinav Kumar Orcid Logo, Jyoti Prakash Singh, Nripendra P. Rana, Yogesh Dwivedi Orcid Logo

Information Systems Frontiers, Volume: 25, Issue: 4, Pages: 1589 - 1604

Swansea University Author: Yogesh Dwivedi Orcid Logo

Check full text

DOI (Published version): 10.1007/s10796-022-10309-x

Abstract

During a disaster, a large number of disaster-related social media posts are widely disseminated. Only a small percentage of disaster-related information is posted by eyewitnesses. The post of a disaster eyewitness offers an accurate depiction of the disaster. Therefore, the information posted by th...

Full description

Published in: Information Systems Frontiers
ISSN: 1387-3326 1572-9419
Published: Springer Science and Business Media LLC 2023
Online Access: Check full text

URI: https://cronfa.swan.ac.uk/Record/cronfa60323
Tags: Add Tag
No Tags, Be the first to tag this record!
Abstract: During a disaster, a large number of disaster-related social media posts are widely disseminated. Only a small percentage of disaster-related information is posted by eyewitnesses. The post of a disaster eyewitness offers an accurate depiction of the disaster. Therefore, the information posted by the eyewitness is preferred over the other source of information as it is more effective at helping organize rescue and relief operations and potentially saving lives. In this work, we propose a multi-channel convolutional neural network (MCNN) that uses three different word-embedding vectors together to classify disaster-related tweets into eyewitness, non-eyewitness, and don’t know classes. We compared the performance of the proposed multi-channel convolutional neural network with several attention-based deep-learning models and conventional machine learning-models such as recurrent neural network, gated recurrent unit, Long-Short-Term-Memory, convolutional neural network, logistic regression, support vector machine, and gradient boosting. The proposed multi-channel convolutional neural network achieved an F1-score of 0.84, 0.88, 0.84, and 0.86 with four disaster-related datasets of floods, earthquakes, hurricanes, and wildfires, respectively. The experimental results show that the training MCNN model with different word embedding together performs better than the conventional machine-learning models and several other deep-learning models.
Keywords: Disaster; Eyewitness tweets; Informative contents; Multi-channel convolutional neural network; Recurrent neural network
College: Faculty of Humanities and Social Sciences
Issue: 4
Start Page: 1589
End Page: 1604

Similar Items