Authors : Manjusha Kausik Duarah

Volume/Issue : Volume 10 - 2025, Issue 11 - November

Google Scholar : https://tinyurl.com/529w2pd4

Scribd : https://tinyurl.com/5wbzvpnp

DOI : https://doi.org/10.38124/ijisrt/25nov1392

Note : A published paper may take 4-5 working days from the publication date to appear in PlumX Metrics, Semantic Scholar, and ResearchGate.

Abstract : The COVID-19 pandemic has significantly impacted global public sentiment, with social media platforms like Facebook, Twitter serving as key outlets for expressing emotions and opinions (Ainapure, et al., 2023). Misinformation and biased narratives on these platforms exacerbate public anxiety, making sentiment analysis crucial for understanding collective emotions (Tsao et al., 2021). This study applies Bidirectional Encoder Representations from Transformers (BERT), a state-of-the-art deep learning model, to classify COVID-19- related tweets and facebook posts into five sentiment categories: Anger, Disgust, Fear, Happiness, Sadness and Surprise. The applied BERT model achieved an accuracy rate of 87.57%, outperforming shallow machine learning modelssuch as Logistic Regression, Support Vector Machines (SVM), and Random Forests. The results obtained highlight the efficiency of BERT in capturing complex sentiments, providing valuable insights to help policymakers address public concerns in times of crisis.

Keywords : Sentiment Analysis, BERT, COVID-19, Deep Learning, Twitter, Natural Language Processing (NLP).

References :

1. Abd-Alrazaq, A., Alhuwail, D., Househ, M., Hamdi, M., & Shah, Z. (2020). Top concerns of tweeters during the COVID-19 pandemic: Infoveillancestudy. Journal of Medical Internet Research, 22(4), e19016. https://doi.org/10.2196/19016.
2. Basiri, M. E., Nemati, S., Abdar, M., Asadi, S., &Acharrya, U. R. (2021). A novel fusion-based deep learning model for sentiment analysis of COVID-19 tweets. Knowledge-Based Systems, 228, 107242. https://doi.org/10.1016/j.knosys.2021.107242.
3. Crawford, K. (2021). Atlas of AI. Yale University Press.
4. Delhi Comparatists. (2021, August 17). Against the Urgency of People Dying in the Streets, Why in God's Name Cultural Studies? /Dilip Kumar Das. YouTube. https://www.youtube.com/watch?v=AXXDcMjsy-I.
5. Devlin, J., Chang, M., Lee, K., &Toutanova, K. (2018). BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. arXiv (Cornell University). https://doi.org/10.48550/arxiv.1810.04805.
6. Jockers, M. (2013). Macroanalysis: Digital Methods and Literary History. University of Illinois Press.
7. Kupcova, I., Danisovic, L., Klein, M., &Harsanyi, S. (2023b). Effects of the COVID-19 pandemic on mental health, anxiety, and depression. BMC Psychology, 11(1). https://doi.org/10.1186/s40359-023-01130-5.
8. Lwin, M. O., Lu, J., Sheldenkar, A., Schulz, P. J., Shin, W., Gupta, R., & Yang, Y. (2020). Global sentiments surrounding the COVID-19 pandemic on Twitter: Analysis of Twitter trends. JMIR Public Health and Surveillance, 6(2), e19447. https://doi.org/10.2196/19447.
9. Moretti, F. (2013). Distant Reading. Verso.
10. Ngai, S. (2005). Ugly Feelings. Harvard University Press.
11. Papacharissi, Z. (2015). Affective Publics. Oxford Uuniversity Press.
12. Postman, N. (1985). Amusing Ourselves to Death. Penguin USA.
13. Sanh, V., Debut, L., Chaumond, J., & Wolf, T. (2019). DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter. arXiv (Cornell University). https://doi.org/10.48550/arxiv.1910.01108.
14. Tsao, S., Chen, H., Tisseverasinghe, T., Yang, Y., Li, L., & Butt, Z. A. (2021). What social media told us in the time of COVID-19: a scoping review. The Lancet Digital Health, 3(3),    e175–e194. https://doi.org/10.1016/s2589-7500(20)30315-0.