Analysis of Twitter Conversation on COVID-19 Pandemic in Africa 2019-2020
Abstract
Background: Communication about COVID-19 pandemic has a huge impact on coordination, control and mitigation efforts against the disease. Patterns and trends of COVID-19 pandemic conversations amongst African tweeps between the year 2019 and 2020 was studied. This study aimed to determine the impact of Twitter COVID-19 information dissemination on attitudes, behaviour and decision making during the pandemic.
Subjects and Method: This was a cohort study with combined quantitative and qualitative approach. This study was conducted in Africa, from December 2019 to December 2020. The quantitative approach was founded on data mining and data analytics research approach, applying measurements in terms of counts, numbers and frequencies while qualitative approach was founded on Natural Language Processing (NPL) algorithm to extract themes/topics and further applying sentiment analysis to a body of large textual data.
Results: A total number of 24,251 tweets was recorded, out of which 9, 016 (37.2%) of the tweets were positive, indicating positive attitude towards COVID-19 related information, control, treatment and regulations. A number of 7, 024 (29%) of tweets were considered neutral, indicating a neutral opinion on conversations related to COVID-19, while 8, 211 (33.9%) were considered negative tweets. South Africa is the most frequently used word and frequently used hashtag followed by Nigeria. Result further revealed four clear topics of discussion which are: a) Africa coronavirus, b) First sub-Saharan pandemic variant, c) Total number of confirmed new deaths, and d) COVID-19 cases in Africa. Besides, it was observed that most health authorities and health partners in Africa are not actively participating on Twitter.
Conclusion: Health information dissemination on social media must be moderated through censorship, otherwise fake news and misinformation would persist to aggravate the spread of diseases and cause deaths. In order to protect the public against false information, public health institutions, governments and partners in health should establish an active presence on social media to share factual information, and timely debunk misinformation.
Keywords: Africa, COVID-19, twitter Conversation, social media, sentiment Analysis
Correspondence:
Sanni Shamsudeen Ademola. Department of Computer Science, Faculty of Science and Engineering, University of Eswatini, Private Bag 4, Matsapha, Manzini, Kingdom of Eswatini. Email: sanniade01@gmail.com. Mobile: +26876241155/79241155
Journal of Health Promotion and Behavior (2021), 06(04): 272-283
DOI: https://doi.org/10.26911/thejhpb.2021.06.04.02
References
Al-Dmour H, Amer SMA, Al-Dmour R (2020). Influence of social media plat-forms on public health protection against the COVID-19 pandemic via the mediating effects of public health awareness and behavioural changes: integrated model. J. Med. Internet Res.22(8): 19996. DOI: 10.2196/-19996
Aslam S (2021). Twitter by the Numbers: Stats, Demographics Fun Facts, Omnicore. Available at: https://www.omnicoreagency.com/twitter-statistics/.
Boon-Itt S, Skunkan Y (2020). Public perception of the COVID-19 pandemic on Twitter: Sentiment analysis and topic modeling study. JMIR. Public Health and Surveillance. 6(4): 21978. DOI: 10.2196/21978.
Bridgman A, Merkley E, Loewen PJ, Owen T, Ruths D, Teichmann L, Zhilin O. (2020). The causes and consequences of COVID-19 misperceptions: Understanding the role of news and social media. Harvard Kennedy School Misinformation Review. 1(3). DOI: 10.31219/osf.io/6tcdn.
Burton SH, Tanner KW, Giraud-carrier CG, West JH (2012). Right Time, Right Place, Health Communication on Twitter: Value and Accuracy of Location Information. 14: 1–11. DOI: 10.37016/mr-2020028.
Collinson S, Khan K, Heffernan JM (2015). The effects of media reports on disease spread and important public health measurements. PloS one. 10(11): 0141423. DOI: 10.1371/journal.pone.0141423.
Gallotti R, Valle F, Castaldo N, Sacco P, Domenico M. (2020). COVID-19 epidemics, Nature Human Behaviour. Springer US. DOI: 10.1038/s41562-020-00994-6.
Giustini D, Ali SM, Fraser M, Boulos MNK (2018). Effective uses of social media in public health and medicine: a systematic review of systematic reviews. Online J. Public Health Inform. 10(2): 215. DOI: 10.5210/ojp-hi.v10i2.8270.
Hazzam J, Abdelmounaim L. (2011) Health care professionals’ social media behaviour and the underlying factors of social media adoption and use: quantitative study. J. Med. Internet Res. 20(18): 12035. DOI: 10.2196/12035.
Hu Z, Yang Z, Li Q, Zhang A (2020). The COVID-19 Infodemic: Infodemiology study analysing stigmatizing search terms. J. Med Internet Res. 22(11).
Kouzy R, Abi JJ, Kraitem A, El-Alam MB, Karam B, Adib E, Zarka J, et al., (2020). Coronavirus Goes Viral: Quantifying the COVID-19 Misinformation Epidemic on Twitter. Cureus, 12(3), e7255. DOI: 10.7759/cureus.7255
Mishori R, Singh LO, Brendan L, Calvin N (2014). Mapping physician Twitter networks: describing how they work as a first step in understanding connectivity, information flow, and message diffusion. J. Med. Internet Res. 16(4): 107. DOI: 10.2196/jmir.3006.
Moorhead SA, Hazlett DE, Harrison L, Carroll JK, Irwin A, Hoving C (2013). A new dimension of health care: systematic review of the uses, benefits, and limitations of social media for health communication. J. Med. Internet Res. 15(4): 1933. DOI: 10.2196/jmir.1933.
Nagendran M, Dimick JB. (2014). Disseminating research findings preparing for generation. JAMA Surg. 49(7): 629–630. DOI: 10.1001/jamasurg.2013.5019.
Park H, Reber BH, Chon MG, Park H, Reber BH, Chon MG. (2016). Tweeting as Health Communication: Health organizations use of twitter for health promotion and public engagement tweeting as health communication: health organizations. Use of Twitter for Health Promotion and Public Engagement. 21(2):188–198. DOI: 10.1080/10810730.2015.1058435
Park H, Rodgers S, Stemmle J. (2013). Analysing health organizations' use of Twitter for promoting health literacy. J. Health Commun. 18(4):410-25. https://doi.org/10.1080/10810730.-2012.727956.
Pérez-Escoda A, Jiménez-Narros C, PerladoLamo EM, Pedrero-Esteban LM (2020). Social networks engagement during the COVID-19 pandemic in Spain: health media vs. healthcare professionals. Int. J. Environ. Res. Public Health. 17(4): 5261. DOI: https://doi.org/10.3390/ijerph17145261.
Reuters (2021). COVID-19 Global tracker, Reuters research. Available at: https://graphics.reuters.com/worldcoronavirus-tracker-and-maps/.
Rufai SR, Bunce C. (2020). World leaders’ usage of twitter in response to the COVID-19 pandemic: A content analysis. J Public Health. 42(3): 510–516. DOI: 10.1093/pubmed/fdaa049.
Sinnenberg L, Buttenheim AM, Padrez K, Mancheno C, Ungar L, Merchant RM (2017). Twitter as a tool for health research: a systematic review. Am J Public Health. 107(1): 1–8. DOI: 10.-21¬05/AJPH.2016.303512.
Wayne W, Chiu XI, Chen Y, Mukherjee T. (2015). Twitter hashtags for health : applying network and content analyses to understand the health knowledge sharing in a Twitter-based community of practice. Quality Quantity. Springer Netherlands. 1361–1380. doi: 10.1007/s11135-014-0051-6.
Xue J, Chen J, Hu R, Chen C, Zheng C, Su Y (2020). Twitter Discussions and Emotions about the COVID-19 Pandemic: Machine Learning Approach. J. Med. Internet Res. 22(11): 1–14. doi: 10.21-96/20550.
Yang Q, Shiwen W (2021). How social media exposure to health information influences Chinese peoples health protective behaviour during air pollution: a theory of planned behaviour perspective. Health communication. 36(3): 324–333. doi: 10.1080/10410-236.2019.1692486.
Zhou J, Liu F, Zhou H (2018). Understanding health food messages on Twitter for health literacy promotion. Perspectives in Public Health: 138(3): 173–179. doi: 10.1177/1757913918760-359.
