Journal of Medical Library and Information Science

Vol. 6 No. 6 (2025)

Sentiment Analysis of COVID-19 Crisis Information on Twitter During Major Outbreak Phases

Journal of Medical Library and Information Science, Vol. 6 No. 6 (2025), 5 April 2025 , Page 1-8
https://doi.org/10.22037/jmlis.v6i6.50584

Abstract

Introduction: The COVID-19 pandemic profoundly transformed global communication practices, with Twitter emerging as a key platform for sharing crisis-related information. This study aims to investigate public emotional dynamics across four critical phases of the pandemic: Emergence, Lockdowns, Vaccine Rollout, and Variant Surges, to capture how sentiment evolved and to highlight implications for crisis communication strategies.

Methods: This study employed a quantitative content analysis method, incorporating sentiment analysis techniques, to assess COVID-19 crisis-related tweets across key phases of the outbreak. A dataset of 2 million COVID-19-related tweets, spanning January 2020 to December 2022, was analyzed using a hybrid sentiment analysis framework. VADER was applied for lexicon-based polarity scoring, while a fine-tuned BiLSTM model enhanced contextual classification. Emotion detection, guided by the NRC Emotion Lexicon, identified eight dominant emotions, including fear, trust, anger, and joy. Comparative analyses were conducted between official sources (such as verified health agencies, government institutions, and news outlets) and citizen-generated content to assess differences in sentiment and emotional tone across the phases.

Results: Two million tweets were analyzed across four key phases of the pandemic. The majority of tweets were citizen-generated (81%). Tweet volume peaked during Phase 1 (the initial outbreak) and Phase 3 (the vaccine rollout). Polarity trends indicated heightened negative sentiment during the initial outbreak and lockdowns, followed by a substantial rise in positivity during the vaccine rollout, and renewed negativity during variant surges. Fear dominated Phase 1 (36.2%), trust rose in Phase 3 (34.7%), and anger was most pronounced during Phase 4 (28.9%). Official sources were significantly more positive in tone compared to citizens across all phases (p < 0.05).

Conclusion: The findings demonstrate the importance of phase-specific, emotion-aware communication strategies. By aligning messaging with prevailing emotional climates, health agencies can reduce public trust vulnerability to misinformation and improve the effectiveness of crisis communication during future global health emergencies.

Keywords:
  • COVID-19
  • Socia media
  • Twitter
  • Sentiment analysis
  • Emotions

How to Cite

Aminu*, M., & Trivedi, M. (2025). Sentiment Analysis of COVID-19 Crisis Information on Twitter During Major Outbreak Phases. Journal of Medical Library and Information Science, 6(6), 1–8. https://doi.org/10.22037/jmlis.v6i6.50584

References

1. Cucinotta D, Vanelli M. WHO declares COVID-19 a pandemic. Acta Bio Medica Atenei Parm. 2020;91(1):157. doi: 10.23750/ABM.V91I1.9397

2. Boon-Itt S, Skunkan Y. Public perception of the COVID-19 pandemic on Twitter: sentiment analysis and topic modeling study. JMIR public Heal Surveill. 2020;6(4). doi: 10.2196/21978

3. Lwin MO, Lu J, Sheldenkar A, Schulz PJ, Shin W, Gupta R, et al. Global Sentiments surrounding the COVID-19 pandemic on Twitter: Analysis of Twitter trends. JMIR public Heal Surveill. 2020;6(2). doi: 10.2196/19447

4. Medford RJ, Saleh SN, Sumarsono A, Perl TM, Lehmann CU. An “Infodemic”: leveraging high-volume Twitter data to understand early public sentiment for the Coronavirus disease 2019 outbreak. Open forum Infect Dis. 2020;7(7). doi: 10.1093/OFID/OFAA258

5. Bhattacharya S, Singh A. Unravelling the infodemic: A systematic review of misinformation dynamics during the COVID-19 pandemic. Front Commun. 2025;10:1560936. doi: 10.3389/FCOMM.2025.1560936/BIBTEX

6. Yang KC, Pierri F, Hui PM, Axelrod D, Torres-Lugo C, Bryden J, et al. The COVID-19 Infodemic: Twitter versus Facebook. Big Data Soc. 2020;8(1). doi: 10.1177/20539517211013861

7. Cinelli M, Quattrociocchi W, Galeazzi A, Valensise CM, Brugnoli E, Schmidt AL, et al. The COVID-19 social media infodemic. Sci Rep. 2020;10(1). doi: 10.1038/S41598-020-73510-5

8. Islam MS, Sarkar T, Khan SH, Kamal AHM, Murshid Hasan SM, Kabir A, et al. COVID-19-related infodemic and its impact on public health: A global social media analysis. Am J Trop Med Hyg. 2020;103(4):1621–9. doi: 10.4269/AJTMH.20-0812

9. Samuel J, Ali GGMN, Rahman MM, Esawi E, Samuel Y. COVID-19 public sentiment insights and machine learning for Tweets classification. Information. 2020;11(6):314. doi: 10.3390/INFO11060314

10. Mathayomchan B, Taecharungroj V, Wattanacharoensil W. Evolution of COVID-19 Tweets about Southeast Asian Countries: Topic modelling and sentiment analyses. Place Brand Public Dipl. 2022;19(3):317–34. doi: 10.1057/S41254-022-00271-5

11. Almutiri M, Alghamdi M, Elazhary H. Sentiment analysis of pandemic Tweets with COVID-19 as a prototype. Int J Adv Comput Sci Appl. 2024;15(4):510–8. doi: 10.14569/IJACSA.2024.0150453

12. Obagbuwa IC, Chibaya O. Sentiment analysis and machine learning approaches in COVID-19 tweets. Int Conf Sci Eng Bus Driv Sustain Dev Goals, SEB4SDG. 2024; 1-7; doi: 10.1109/SEB4SDG60871.2024.10629896

13. Jalil Z, Abbasi A, Javed AR, Badruddin Khan M, Abul Hasanat MH, Malik KM, et al. COVID-19 related sentiment analysis using State-of-the-Art machine learning and deep learning techniques. Front Public Health. 2022;9. doi: 10.3389/FPUBH.2021.812735

  • Abstract Viewed: 39 times
  • e76 (PDF) Downloaded: 1 times

Download Statastics

Make a Submission

Make a Submission

Current Issue