Tweet Topics and Sentiments Relating to COVID-19 Vaccination Among Australian Twitter Users: Machine Learning Analysis

Journal of Medical Internet Research - Tập 23 Số 5 - Trang e26953
Stephen Wai Hang Kwok1, Sai Kumar Vadde2, Guanjin Wang2
1School of Nursing, The Hong Kong Polytechnic University, Hong Kong, China (Hong Kong)
2Discipline of Information Technology, Media and Communications, Murdoch University, Perth, Australia

Tóm tắt

BackgroundCOVID-19 is one of the greatest threats to human beings in terms of health care, economy, and society in recent history. Up to this moment, there have been no signs of remission, and there is no proven effective cure. Vaccination is the primary biomedical preventive measure against the novel coronavirus. However, public bias or sentiments, as reflected on social media, may have a significant impact on the progression toward achieving herd immunity.ObjectiveThis study aimed to use machine learning methods to extract topics and sentiments relating to COVID-19 vaccination on Twitter.MethodsWe collected 31,100 English tweets containing COVID-19 vaccine–related keywords between January and October 2020 from Australian Twitter users. Specifically, we analyzed tweets by visualizing high-frequency word clouds and correlations between word tokens. We built a latent Dirichlet allocation (LDA) topic model to identify commonly discussed topics in a large sample of tweets. We also performed sentiment analysis to understand the overall sentiments and emotions related to COVID-19 vaccination in Australia.ResultsOur analysis identified 3 LDA topics: (1) attitudes toward COVID-19 and its vaccination, (2) advocating infection control measures against COVID-19, and (3) misconceptions and complaints about COVID-19 control. Nearly two-thirds of the sentiments of all tweets expressed a positive public opinion about the COVID-19 vaccine; around one-third were negative. Among the 8 basic emotions, trust and anticipation were the two prominent positive emotions observed in the tweets, while fear was the top negative emotion.ConclusionsOur findings indicate that some Twitter users in Australia supported infection control measures against COVID-19 and refuted misinformation. However, those who underestimated the risks and severity of COVID-19 may have rationalized their position on COVID-19 vaccination with conspiracy theories. We also noticed that the level of positive sentiment among the public may not be sufficient to increase vaccination coverage to a level high enough to achieve vaccination-induced herd immunity. Governments should explore public opinion and sentiments toward COVID-19 and COVID-19 vaccination, and implement an effective vaccination promotion scheme in addition to supporting the development and clinical administration of COVID-19 vaccines.

Từ khóa


Tài liệu tham khảo

10.1016/S0140-6736(20)30183-5

Countries/areas with reported cases of Coronavirus Disease 2019 (COVID 19) (Last updated on January 4, 2021, 11 am)Hong Kong Centre for Health Protection20202021-05-06https://www.chp.gov.hk/files/pdf/statistics_of_the_cases_novel_coronavirus_infection_en_20210104.pdf

Coronavirus (COVID-19) current situation and case numbersAustralian Department of Health20202021-05-06https://tinyurl.com/uu5semny

WHO coronavirus disease (COVID-19) dashboardWorld Health Organization20202020-09-22https://covid19.who.int/

10.1002/pa.2372

10.1111/cwe.12349

10.3138/jammi-2020-0030

10.1002/jmv.26326

10.1016/j.jinf.2020.03.041

10.1371/journal.pone.0234765

10.7759/cureus.8188

10.1080/17476348.2020.1804365

10.1111/jop.13019

10.3961/jpmph.20.076

10.1371/journal.pone.0242128

10.1016/j.jinf.2020.08.033

10.2217/fvl-2020-0137

10.1016/j.dsx.2020.07.022

Spencer, JP, 2017, American Academy of Family Physicians, 95, 786

10.1542/peds.2014-1079

10.1093/cid/cir007

10.1016/j.jaut.2017.03.011

10.15761/gimci.1000196

10.7759/cureus.2919

Wakefield, AJ, 1998, Lancet, 351, 637, 10.1016/S0140-6736(97)11096-0

10.1016/s0140-6736(99)01239-8

10.1542/peds.108.4.e58

10.1016/s0264-410x(01)00097-4

10.1586/14760584.3.1.19

10.1016/s0140-6736(98)24018-9

10.1016/s0140-6736(99)00160-9

10.1016/s0140-6736(10)60175-4

10.4103/0022-3859.173187

10.1016/S0140-6736(20)31604-4

10.1016/s0140-6736(20)31605-6

The push for a COVID-19 vaccineWorld Health Organization20202020-09-22https://www.who.int/emergencies/diseases/novel-coronavirus-2019/covid-19-vaccines

Immunization schedulesUS Centers for Disease Control and Prevention20202021-05-06https://www.cdc.gov/vaccines/schedules/hcp/schedule-changes.html

FDA insight: Vaccines for COVID-19, Part 1US Food and Drug Administration20202021-05-06https://www.fda.gov/news-events/fda-insight/fda-insight-vaccines-covid-19-part-1

Distributing vaccines and treatments for COVID-19 and fluUK Department of Health and Social Care20202021-05-06https://www.gov.uk/government/consultations/distributing-vaccines-and-treatments-for-covid-19-and-flu

10.2196/jmir.986

10.1016/j.vaccine.2011.11.112

Smallpox vaccinesWorld Health Organization20165312021-05-06https://www.who.int/csr/disease/smallpox/vaccines/en/

10.1016/j.jceh.2020.06.003

10.3389/fphar.2020.00937

10.1016/s1473-3099(20)30559-4

New deal secures potential COVID-19 vaccine for every AustralianPrime Minister of Australia20208212021-05-06CanberraAustralian Governmenthttps://www.health.gov.au/news/new-deal-secures-potential-covid-19-vaccine-for-every-australian-0

10.1038/d41586-020-02633-6

10.1136/bmj.m3967

10.1186/s12911-017-0469-6

10.1177/1460458217740723

10.1080/21645515.2020.1714311

10.3390/ijerph17155394

10.1136/bmj.m2184

10.1177/1329878x20946113

10.2196/19458

Investor fact sheetTwitter20202021-05-06https://s22.q4cdn.com/826641620/files/doc_financials/2019/q4/Q4_19_InvestorFactSheet.pdf

10.26483/ijarcs.v8i8.4716

10.1145/3185045

10.1186/s13326-017-0120-6

10.3390/ijerph17103464

10.21105/joss.01829

RinkerTWqdapRegex: Regular expression removal, extraction, and replacement tools, version 0.7.2qdapRegex20172021-05-06Buffalo, NYUniversity at Buffalohttp://github.com/trinker/qdapRegex

10.18637/jss.v025.i05

FeinererIHornikKtm: Text mining package. R package, version 0.7-8CRAN20202021-05-06https://CRAN.R-project.org/package=tm

HonnibalMMontaniIVan LandeghemSBoydAspaCy: Industrial-strength natural language processing in PythonZenodo20202020-12-23https://doi.org/10.5281/zenodo.1212303

ŘehůřekRSojkaPSoftware framework for topic modelling with large corpora2010LREC Workshop on New Challenges for NLP FrameworksMay 22Valletta, MaltaELRA4550

Sedgewick, R, 2014, Algorithms, 4th edition

Abstract service stopword listSAO/NASA Astrophysics Data System20202020-11-07http://adsabs.harvard.edu/abs_doc/stopwords.html

RobinsonDMisraKSilgeJwidyr: Widen, process, and re-tidy a datasetCRAN20202021-05-06https://cran.r-project.org/web/packages/widyr/index.html

10.1213/ANE.0000000000002864

10.1016/j.tjem.2018.08.001

Blei, DM, 2003, Journal of Machine Learning Research, 3, 993

10.2196/jmir.6045

10.1016/j.vaccine.2020.07.054

NikitaMChaneyNldatuning: Tuning of the latent Dirichlet allocation models parametersCRAN20202021-05-06https://cran.r-project.org/web/packages/ldatuning/index.html

Arun, R, 2010, Advances in Knowledge Discovery and Data Mining. PAKDD 2010. Lecture Notes in Computer Science, vol 6118, 391

10.1016/j.neucom.2008.06.011

10.1073/pnas.0307752101

10.3166/dn.17.1.61-84

10.18637/jss.v040.i13

JockersMLSyuzhet: Extract sentiment and plot arcs from textGitHub20152021-05-06https://github.com/mjockers/syuzhet

10.3115/v1/p14-5010

MohammadSTurneyPEmotions evoked by common words and phrases: Using Mechanical Turk to create an emotion lexicon2010NAACL-HLT 2010 Workshop on Computational Approaches to Analysis and Generation of Emotion in TextJuneLos Angeles, CA

10.1111/j.1467-8640.2012.00460.x

10.2105/ajph.2020.305940

10.1016/j.eswa.2018.09.009

10.1016/j.vaccine.2017.04.060

10.1136/bmjopen-2017-016869

10.1080/21645515.2019.1596712

10.1080/21645515.2019.1627821

Nguyen, D, 2013, "How old do you think I am?": A study of language and age in Twitter, 439

10.1371/journal.pone.0115545

10.1371/journal.pone.0183537

10.1093/infdis/jiaa691

10.15585/mmwr.mm6941e1

10.1038/s41591-020-0962-9

10.1016/b978-0-12-558701-3.50007-7

10.1073/pnas.1702247114

10.1007/s10900-020-00958-x

10.1016/j.eclinm.2020.100495

10.1016/j.lanepe.2020.100012

10.1038/s41467-020-20226-9

10.2196/jmir.3416

10.3390/ijerph17144988

10.1080/00330124.2017.1288577

Thông tin
Thông tin xuất bản

Journal of Medical Internet Research

Tập 23 Số 5

e26953

Thông tin tác giả