Identification of Insecurity in COVID-19 Using Machine Learning Techniques
Somashri Pal Kar, Afiur Rahaman Molla, Sayak Das, Ritam Rajak, Soumyadeep Sil, Avijit Kumar Chaudhuri
Copyright: © 2024
|Pages: 18
DOI: 10.4018/979-8-3693-2105-8.ch016
Abstract
During the pandemic COVID-19, many people died due to the infection caused by the deadly virus, and many affected people in the isolated ward developed mental trauma and feelings of insecurity. In this chapter, the authors study 90 features of collected data from 207 concerned people during what they faced in lockdown period using machine learning about the insecurity to obtain key features. They have chosen seven ML algorithms like logistic regression, naïve bayes, stochastic gradient descent J48, multi-layer perceptron, random forest, and random tree. These algorithms are used on the features to identify appropriate features on insecurity. Data splitting with 10-fold cross validation reduced 90 features into seven features by comparative analysis. In 66-34 split, 50-50 split, 80-20 split, LR and NB achieved above 90% accuracy with these seven features. 80-20 and in 10-fold we get approximately 100% accuracy in J48, MLP, RF, and RT algorithms. Three feature selection techniques, Information Gain, ReliefF and OneR, were used for ranking features based on model performance.
Top1. Introduction
The Covid 19 or coronavirus disease which was first detected in Wuhan City in the Peoples Republic of China is a very deadly virus and is generally transmitted from one person to another through respiratory droplets, sneezing, and coughing, bare hand touch. The virus generally makes its space through the openings of the pores of mouth, nasal tract and ultimately reaches the human lungs causing tremendous breathing problem ultimately causing the death of the people. In most of the cases the Covid affected people are generally kept in isolated ward in hospital or in home quarantine mode where there would be no form of physical touch from the patient to the visitor/reliever/doctor.
The doctor needs to wear a special type of personal protective equipment suit to visit the patient for checking by which no mode of touch or contamination with patient generally happens. In this way during treatment the patient had to be kept in isolation for several months, thus the patient develops a sense of loneliness and thus develops a series of several mental illness, depressions and trauma (Chaudhuri, Sinha, Banerjee et al, 2021). He develops a sense of insecurity that no one is there to talk to him, help him or sit by him to gossip or chat, the whole day he feels to be in prison developing more and more mental depressions and a deep sense of insecurity gets confined inside him, sometimes this sense of insecurity is so advanced that one tries to end up his life (Kim et al., 2021). Standing in this point of view, with the help of Machine Learning and Artificial Intelligence we would like to study about the features of the intense insecurity of the concerned affected people as shown in Figure 1.
Figure 1. The features of the intense insecurity of the concerned affected people
Alt-text: Figure 1 depicts the features of the intense insecurity of the concerned affected people.
Top2. Literature Review
In the article “Self-esteem in a broad-spectrum approach for mental health promotion” by Michael Mann el et al. (2004) research results show beneficial outcomes of positive self-esteem, which is seen to be associated with mental well-being, happiness, adjustment, success, academic achievements and satisfaction. It is also associated with better recovery after severe diseases. In the article “Mental Health Inequalities during COVID-19 Outbreak by Nele Claes al et al (2021) research showed an important role of trait anxiety, conceived of as an individual difference variable and associated with SES.
In the article “A Literature Review on the Connection between Stress and Self-Esteem” by Michael J. Galanaksiel et al. (2016) studies show that self-esteem is associated directly and indirectly to the development of depression. Specifically, low self-esteem combined with stress is risk factors for developing depression. In the article “The association between uncertainty and mental health: a scoping review of the quantitative literature” by Alexandro Massazzael et al. (2023) it is found that one hundred and one papers addressing the association between uncertainty and mental health were identified.