A hybrid deep learning and NLP based system to predict the spread of Covid-19 and unexpected side effects on people

Abstract

The aim of this paper is to deeply analyze the unexpected side effects of people during the Covid-19 pandemic using the RNN based NLP sentiment analysis model. The normalized correlation values that is obtained by computing the cases values between the people behavior extracted and covid-19 reported case also has values close to 1 million by the end of June 2020 provided in dataset. In this research work, with more time, we would like to continue from the results we have achieved by training the RNN with NLP based sentiment analysis model for more extended periods of time for predicting the behavior of people during Covid-19 pandemic with 76.71% of accuracy which is high as compared to the CNN, such as days or weeks, in order to see how results can improve. The advancement in this field created an urge in me to research more on the techniques and methodologies developed for covid-19 extraction. During the outbreak of an epidemic, it is of immense interest to monitor the effects of containment measures and forecast of outbreak including epidemic peak affecting the behavior of people. To confront the change in behavior, a simple RNN based NLP sentiment analysis model is used to simulate the number of affected patients of Coronavirus disease. Our initial problem formulation involved investigating the ideal conditions and preprocessing for working with a specific NLP task: predicting the behavior during the specific time of May 20 – June 20 in 2020 for all four traits of common people during the Covid-19 pandemic.