Detecting COVID-19 Pandemic Using Sentiment Analysis of Tweets

Abstract

From 2019, the world is facing an unforeseen challenge in the form of COVID- 19, which started in Wuhan (China), and within two months, it spread to 212 countries. The coronavirus disease (COVID-19) pandemic puts unprecedented pressure on healthcare systems worldwide. Due to its rapid widespread around the globe affecting the lives of millions, extensive measures to reduce and prevent its transmission have been implemented. One of which is to shut down their cities completely. During this Pandemic, people started to express their situations through social media tools. In natural language processing, valuable insights can be captured from textual data taken from different social media platforms. In this research work, data related to COVID-19 is collected from a popular social networking site, Twitter. The tweets gathered are refined through pre-processing for text mining and sentiment analysis. From this data, we successfully detect the actual count of people who may be affected by the COVID-19 Pandemic using sentimental analysis and machine learning techniques.

Keywords

• twitter
• COVID-19
• sentiment analysis
• machine learning
• data mining

References

1. [1] Joe Hasell, E. M., Diana Beltekian, Bobbie Macdonald, Charlie Giattino, Esteban Ortiz-Ospina, Hannah Ritchie, and Max Roser (2020). "Coronavirus (COVID-19) Testing." from https://ourworldindata.org/coronavirustesting.
2. [2] Worldometer (2020). "Worldometer COVID-19 Data." from https://www.worldometers.info/coronavirus/.
3. [3] Joe Hasell, E. M., Diana Beltekian, Bobbie Macdonald, Charlie Giattino, Esteban Ortiz-Ospina, Hannah Ritchie, and Max Roser (2020). "Coronavirus (COVID-19) Testing." from https://ourworldindata.org/coronavirustesting.
4. [4] Clement, J. (2020). "Number of social network users worldwide from 2010 to 2023." from https://www.statista.com/statistics/278414/number-of-worldwide-social-network-users/.
5. [5] Brew, S. (2020). "100 Social Media Statistics For Marketers in 2020 ". from https://statusbrew.com/insights/social-media-statistics-2020/.
6. [6] Santos, J. C. and Matos, S. (2014). Analyzing Twitter and web queries for flu trend prediction. Theoretical Biology and Medical Modelling, 11(1): S6.
7. [7] Fung, I. C.-H., Fu, K.-W., Ying, Y., Schaible, B., Hao, Y., Chan, C.-H., and Tse, Z. T.-H. (2013). Chinese social media reaction to the mers-cov and avian influenza a (h7n9) outbreaks. Infectious diseases of poverty, 2(1):31.
8. [8] Culotta, A. (2010). Towards detecting influenza epidemics by analyzing twitter messages. In Proceedings of the first workshop on social media analytics, pages 115–122. Acm

9. [9] Chew, C. and Eysenbach, G. (2010). Pandemics in the age of twitter: content analysis of tweets during the 2009 h1n1 outbreak. PloS one, 5(11):e14118.
10. [10] Ahmed, W., Bath, P. A., Sbaffi, L., and Demartini, G. (2018). Moral panic through the lens of twitter: An analysis of infectious disease outbreaks. In Proceedings of the 9th International Conference on Social Media and Society, pages 217–221. ACM.
11. [11] Aslam, A. A., Tsou, M.-H., Spitzberg, B. H., An, L., Gawron, J. M., Gupta, D. K., Peddecord, K. M., Nagel, A. C., Allen, C., Yang, J.-A., et al. (2014). The reliability of tweets as a supplementary method of seasonal influenza surveillance. Journal of medical Internet research, 16(11):e250.