Open Access

ARTICLE

Automatic Surveillance of Pandemics Using Big Data and Text Mining

by Abdullah Alharbi^1,*, Wael Alosaimi¹, M. Irfan Uddin²

1 Department of Information Technology, College of Computers and Information Technology, Taif University, P.O. Box 11099, Taif, 21944, Saudi Arabia
2 Institute of Computing, Kohat University of Science and Technology, Kohat, 26000, Pakistan

* Corresponding Author: Abdullah Alharbi. Email:

(This article belongs to the Special Issue: Deep Learning and Parallel Computing for Intelligent and Efficient IoT)

Computers, Materials & Continua 2021, 68(1), 303-317. https://doi.org/10.32604/cmc.2021.016230

Received 27 December 2020; Accepted 28 January 2021; Issue published 22 March 2021

Abstract

COVID-19 disease is spreading exponentially due to the rapid transmission of the virus between humans. Different countries have tried different solutions to control the spread of the disease, including lockdowns of countries or cities, quarantines, isolation, sanitization, and masks. Patients with symptoms of COVID-19 are tested using medical testing kits; these tests must be conducted by healthcare professionals. However, the testing process is expensive and time-consuming. There is no surveillance system that can be used as surveillance framework to identify regions of infected individuals and determine the rate of spread so that precautions can be taken. This paper introduces a novel technique based on deep learning (DL) that can be used as a surveillance system to identify infected individuals by analyzing tweets related to COVID-19. The system is used only for surveillance purposes to identify regions where the spread of COVID-19 is high; clinical tests should then be used to test and identify infected individuals. The system proposed here uses recurrent neural networks (RNN) and word-embedding techniques to analyze tweets and determine whether a tweet provides information about COVID-19 or refers to individuals who have been infected with the virus. The results demonstrate that RNN can conduct this analysis more accurately than other machine learning (ML) algorithms.

---

Keywords

---

Citations