Machine Learning based Sentiment Analysis of COVID-19 Vaccination Drive in India
Main Article Content
Abstract
SARS-CoV-2 or commonly known as COVID-19 has affected more than 95 million population and two million deaths throughout the world. While the majority of the world has faced lockdown in the year 2020, it has become infeasible to continue with it. In such a scenario, the necessity of vaccination has become eminent. India, being the second most affected country from COVID-19 announced its vaccination drive from 16th January 2021, after the Central Drugs and Standards Committee (CDSCO) formally approved vaccines by Bharat Biotech and Serum Institute of India (SII) viz. COVISHIELD and COVAXIN. The government strengthened vaccine drive to ensure immunity to the citizens of the country. However, there is a section of the community which is unconvinced of the COVID-19 vaccination. This research work has been conducted to analyze the sentiments related to tweets from India regarding these two vaccines. The analysis shows that while a majority of the population is having positive sentiments towards these vaccines with some negative sentiments. A comparative analysis was carried out and it was found that TextBlob performed better in sentiment classification than the NRC Lexicon approach.
Article Details
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
References
World Health Organization. Behavioural Considerations for Acceptance and Uptake of COVID-19 Vaccines: WHO Technical Advisory Group on Behavioural Insights and Sciences for Health; Meeting Report, 15 October 2020; World Health Organization: Geneva, Switzerland, 2020.
I. Allagui; Breslow, H. social media for public relations: Lessons from four effective cases, Public Relat. Rev., 42, (2016), 20-30.
C. Valentini; Is using social media “good” for the public relations profession? A critical reflection, Public Relat. Rev., 41 (2015), 170-177.
World Health Organization. Guidance on Developing a National Deployment and Vaccination Plan for COVID-19 Vaccines: Interim Guidance, 16 November 2020; World Health Organization: Geneva, Switzerland, 2020.
O.B. Driss, S. Mellouli and Z. Trabelsi; From citizens to government policy-makers: Social media data analysis, Gov. Inf. Q. 36, (2019), 560-570.
T. Yigitcanlar, N. Kankanamge, A. Preston, P.S. Gill, M. Rezayee, M. Ostadnia, B. Xia and G. Ioppolo; How can social media analytics assist authorities in pandemic-related policy decisions? Insights from Australian states and territories, Health Inf. Sci. Syst. 8, (2020), 1-21.
Q. Liao, J. Yuan, M. Dong, L. Yang, R.;Fielding, W.W.T. Lam; Public engagement, and government responsiveness in the communications about COVID-19 during the early epidemic stage in China: infodemiology study on social media data, J. Med. Internet Res. 22, (2020), e18796.
M. Taboada, J. Brooke, M. Tofiloski, K. Voll, M. Stede; Lexicon-based methods for sentiment analysis, Comput. Linguist., 37, (2011), 267-307.
B. Liu; Opinion mining and sentiment analysis, Web Data Mining (2011), 459-526.
Y. Garg, N. Chatterjee; Sentiment analysis of twitter feeds, Proceedings of the International Conference on Big Data Analytics,New Delhi, India, 20-23 December 2014; Springer: Berlin/Heidelberg, Germany, (2014), 33-52.
I. El Alaoui, Y. Gahi, R. Messoussi, Y. Chaabi, A. Todoskoff, A. Kobi; A novel adaptable approach for sentiment analysis on bigsocial data, J. Big Data, 5, (2018), 12.
J.F. Sánchez-Rada, Iglesias, C.A. CRANK; A Hybrid Model for User and Content Sentiment Classification Using Social Contextand Community Detection, Appl. Sci., 10, (2020), 1662.
S. Loria; TextBlob Documentation. Release 0˙15, 2, (2018), 269.