Analyzing The Mental Health Status of Social Media Users During The Outbreak of Coronavirus

In December 2019, the SARS-CoV-2 coronavirus caused a sudden outbreak of COVID-19 disease in China. According to the World Health Organization, till now, tens of millions of confirmed COVID-19 cases and hundreds of thousands deaths have been reported worldwide. Meanwhile, countries are facing unprecedented pressure to provide the appropriate conditions for controlling population through case assessments and the proper use of available resources. The rapid increase in the number of cases worldwide has become a source of fear and anxiety among the people. Social networks are one of the real world resources for analyzing any incidents. The analysis of emotions and mental status in order to achieve the behavioral pattern of individuals based on their activities in social media is one of the most important aspects to consider. In this article, we will present a method based on deep learning in order to identify emotions and its severity and to provide a behavioral pattern of individuals and finally to classify each one into one of three health (neutral), at risk and infected categories using a fuzzy system. The results of simulations and comparisons show improved detection of the proposed method.

Keywords: Emotion analysis; Behavior measurement; Coronavirus; Deep learning