Abstract—According to the WHO, Covid-19 is an illness caused by a novel coronavirus scientifically known as SARS-CoV2. This virus was first discovered in late December 2019, when a cluster of pneumonia cases was reported from Wuhan, China. Since then, the virus has continued to spread and cases have grown rapidly, leading to 74.3 million cases worldwide and 1.65 million deaths in within the span of a year.
According to Dr. Sanil Rege, a psychiatrist, the effects of quarantining and social distancing include multiple stressors affect a person during a time of isolation. For instance, a person could have unpleasant experiences due to loss of freedom, separation from significant people in their lives, fear, financial stability, and lack of supplies. These factors can strongly lead to the development of stress symptoms such as irritability, insomnia, temper issues, emotional burnout, and overall low mental health. As such, the Covid-19 pandemic has affected the normalcy of life throughout the world and many people have taken to social media platforms such as Twitter to express their thoughts and feelings.
In order to understand the type of discussions taking place regarding Covid-19 and to recognize major topics of concern, the relationship between tweet sentiment and Covid-19 casualties are analyzed, then, Tweet text is examined to identify frequently used words, hashtags, and mentioned users. Covid-19 keyword containing tweets are downloaded using Tweepy to a database and analyzed for sentiment by NLTK Vader. Results suggest a moderate positive correlation between negative sentiment and Covid-19 cases and deaths.
Index Terms—COVID-19, Twitter, sentiment analysis, social media.
Amrutha Ragothaman was with School of Computer Science and Technology, Kean University, Union, NJ, 07083 USA (e-mail: ragothaa@kean.edu). Ching-yu Huang is with the School of Computer Science & Technology, Kean University, Union, NJ 07083, USA (e-mail: chuang@kean.edu).
[PDF]
Cite:Amrutha Ragothaman and Ching-Yu Huang, "Sentiment Analysis on Covid-19 Twitter Data," International Journal of Computer Theory and Engineering vol. 13, no. 4, pp. 100-107, 2021.
Copyright © 2021 by the authors. This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited (CC BY 4.0).