To Judge Depression and Mental Illness on Social Media Using Twitter

Abstract

At present the pandemic situation caused by Corona virus syndrome 2019 which is abbreviated as COVID-19, has made the lifespan of men at stake. Not only has it affected the economic condition and created health hazards of the peoples all over the world but also it tells upon their mental state. It is surprising but very difficult to assess the frequency. There are various reasons behind this mental disorder. They are recession from work, confined in house strategy, getting afraid of corona virus, and some more. In this paper, we focus on the use of Natural Language Processing (NLP) procedure to analyze tweets with regard to mental state. Training of significant prototypes has been provided to categorize all tweets into the emotions mentioned below: covid19, covid, COVID-19, covid 19, flu, virus, hantavirus, fever, cough, social distance, lockdown, pandemic, epidemic. We build the EmoCT (Emotion-Covid19-Tweet) dataset to train physically, tagging 1,500 English tweets. In addition to it, two procedures are suggested and distinguished to explore the causes which are creating melancholy and disquiet.