Sentiment Analysis based Emotion Extraction for COVID-19 Using Crawled Tweets and Global Statistics for Mental Health

Area of Science:

• Public Health
• Mental Health
• Data Science

Background:

• The COVID-19 pandemic presented unprecedented global challenges, affecting over 213 countries.
• Implemented control measures like lockdowns and travel bans did not prevent the disease's spread or its severe consequences.
• The pandemic's impact on financial, social, and physical well-being led to widespread psychological and mental health issues.

Purpose of the Study:

• To quantitatively analyze the prevalence of depression, stress, and suicide during the COVID-19 pandemic.
• To specifically examine these mental health trends globally and within India.
• To understand public emotional responses during the pandemic through sentiment analysis of social media data.

Main Methods:

• Global data, including tweets, were collected using a web scraper.
• Data analysis was performed using Tableau for quantitative insights.
• Sentiment analysis was conducted using Python to extract emotions (Fear, Sadness, Anger, Happiness) from tweets.

Main Results:

• A total of 819,678 tweets were collected from January 2020 to March 2022.
• Quantitative analysis revealed significant increases in depression, stress, and suicide cases globally and in India.
• Sentiment analysis indicated that Fear (59.3%) and Sadness (28.9%) were the dominant emotions expressed in tweets.

Conclusions:

• The COVID-19 pandemic has had a profound negative impact on global mental health.
• Public sentiment during the pandemic was largely characterized by fear and sadness.
• Data-driven approaches, including social media analysis, are crucial for understanding and addressing mental health crises.