Rapid assessment of communication consistency: sentiment analysis of public health briefings during the COVID-19 pandemic

Okan Bulut; Cheryl N. Poth; Okan Bulut; Cheryl N. Poth

doi:10.3934/publichealth.2022020

AIMS Public Health

2022, Volume 9, Issue 2: 293-306. doi: 10.3934/publichealth.2022020

Previous Article Next Article

Research article Topical Sections

Rapid assessment of communication consistency: sentiment analysis of public health briefings during the COVID-19 pandemic

Okan Bulut ^,,
Cheryl N. Poth

Centre for Research in Applied Measurement and Evaluation, Faculty of Education, University of Alberta, Edmonton, AB, Canada

Received: 27 December 2021 Revised: 21 January 2022 Accepted: 25 January 2022 Published: 10 February 2022

Background
A key component of the initial public health response to the COVID-19 pandemic involved the use of mass media briefings led by public health officials to communicate updates during a time of great uncertainty and rapidly changing information. This study aims to examine the consistency of communications expressed during the public health briefings to generate novel insights about the type, direction, and strength of public health messages. The data source included 131 readily accessible public health briefings alongside the provincial and national new confirmed case counts during the first two waves of rapidly increasing cases during the pandemic in Alberta, Canada. We employed sentiment analysis as a text mining technique to explore the types and frequency of words in public health briefings conveying positive and negative sentiments. Using statistical analyses and data visualizations, we examined how public health messaging shifted with case trends.
Results
Our findings indicate consistent public health messaging in terms of sentiments regardless of case count fluctuations, an association of specific words with conveying positive and negative sentiments, and a focus on particular message patterns at different points during the first two waves of the COVID-19 pandemic.
Conclusion
Our findings demonstrate the practical implications and methodological advantages of using sentiment analysis as a data analytics tool for rapidly and objectively assessing the consistency of health communications during a public health crisis.
- COVID-19,
- public health informatics,
- data mining,
- sentiment analysis,
- communication
Citation: Okan Bulut, Cheryl N. Poth. Rapid assessment of communication consistency: sentiment analysis of public health briefings during the COVID-19 pandemic[J]. AIMS Public Health, 2022, 9(2): 293-306. doi: 10.3934/publichealth.2022020

Related Papers:

Abstract

Background

A key component of the initial public health response to the COVID-19 pandemic involved the use of mass media briefings led by public health officials to communicate updates during a time of great uncertainty and rapidly changing information. This study aims to examine the consistency of communications expressed during the public health briefings to generate novel insights about the type, direction, and strength of public health messages. The data source included 131 readily accessible public health briefings alongside the provincial and national new confirmed case counts during the first two waves of rapidly increasing cases during the pandemic in Alberta, Canada. We employed sentiment analysis as a text mining technique to explore the types and frequency of words in public health briefings conveying positive and negative sentiments. Using statistical analyses and data visualizations, we examined how public health messaging shifted with case trends.

Results

Our findings indicate consistent public health messaging in terms of sentiments regardless of case count fluctuations, an association of specific words with conveying positive and negative sentiments, and a focus on particular message patterns at different points during the first two waves of the COVID-19 pandemic.

Conclusion

Our findings demonstrate the practical implications and methodological advantages of using sentiment analysis as a data analytics tool for rapidly and objectively assessing the consistency of health communications during a public health crisis.

Acknowledgments

The research leading to these results received funding from the University of Alberta's Endowment Fund for the Support for the Advancement of Scholarship (SAS) Program. The authors would like to thank Adrienne Montgomerie who provided feedback and editing advice.

Conflict of interest

The authors declare no conflict of interest.

References

[1]	Ratzan SC, Gostin LO, Meshkati N, et al. (2020) COVID-19: An urgent call for coordinated, trusted sources to tell everyone what they need to know and do. J Health Commun 25: 747-749. https://doi.org/10.1080/10810730.2020.1894015
[2]	Ratzan SC, Sommariva S, Rauh L (2020) Enhancing global health communication during a crisis: lessons from the COVID-19 pandemic. Public Health Res Pract 30: 3022010. https://doi.org/10.17061/phrp3022010
[3]	Austin EW, Austin BW, Willoughby JF, et al. (2021) How media literacy and science media literacy predicted the adoption of protective behaviors amidst the COVID-19 pandemic. J Health Commun 26: 239-252. https://doi.org/10.1080/10810730.2021.1899345
[4]	Benham JL, Lang R, Burns KK, et al. (2021) Attitudes, current behaviours and barriers to public health measures that reduce COVID-19 transmission: A qualitative study to inform public health messaging. Plos One 16: e0246941. https://doi.org/10.1371/journal.pone.0246941
[5]	Yamanis T Clear, consistent health messaging critical to stemming epidemics and limiting coronavirus deaths (2020). Available from: https://theconversation.com/clear-consistent-health-messaging-critical-to-stemming-epidemics-and-limiting-coronavirus-deaths-134529
[6]	Austin L, Fisher LB, Jin Y (2012) How audiences seek out crisis information: exploring the social-mediated crisis communication model. J Appl Commun Res 40: 188-207. https://doi.org/10.1080/00909882.2012.654498
[7]	Maitlis S, Sonenshein S (2010) Sensemaking in crisis and change: inspiration and insights from Weick (1988). J Manage Stud 47: 551-580. https://doi.org/10.1111/j.1467-6486.2010.00908.x
[8]	Reynolds B, Seeger MW (2005) Crisis and emergency risk communication as an integrative model. J Health Commun 10: 43-55. https://doi.org/10.1080/10810730590904571
[9]	Latkin CA, Dayton L, Strickland JC, et al. (2020) An assessment of the rapid decline of trust in US sources of public information about COVID-19. J Health Commun 25: 764-773. https://doi.org/10.1080/10810730.2020.1865487
[10]	Centers for Disease Control and PreventionCrisis and emergency risk communication (CERC) manual (2018). Available from: https://emergency.cdc.gov/cerc/manual/index.asp
[11]	World Health OrganizationCommunicating risk in public health emergencies: A WHO guideline for emergency risk communication (ERC) policy and practice (2017). Available from: https://apps.who.int/iris/bitstream/handle/10665/259807/9789241550208-eng.pdf
[12]	Agrawal N, Menon G, Aaker JL (2007) Getting emotional about health. J Mark Res 44: 100-113. https://doi.org/10.1509/jmkr.44.1.100
[13]	Aslam F, Awan TM, Syed JH, et al. (2020) Sentiments and emotions evoked by news headlines of coronavirus disease (COVID-19) outbreak. Hum Soc Sci Commun 7: 1-9. https://doi.org/10.1057/s41599-020-0523-3
[14]	Kwan JSL, Lim KH (2020) Understanding public sentiments, opinions and topics about COVID-19 using Twitter. 2020 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining (ASONAM).IEEE. Available from: https://ieeexplore.ieee.org/abstract/document/9381384
[15]	Sasidharan S, Singh DH, Vijay S, et al. (2020) COVID-19: Pan(info)demic. Turk J Anaesthesiol 48: 438-442. https://doi.org/10.5152/TJAR.2020.1008
[16]	Poth CN, Bulut O, Aquilina AM, et al. (2021) Using data mining for rapid complex case study descriptions: example of public health briefings during the onset of the COVID-19 pandemic. J Mix Method Res 15: 1-26. https://doi.org/10.1177/15586898211013925
[17]	Yi J, Nasukawa T, Bunescu R, et al. (2003) Sentiment analyzer: Extracting sentiments about a given topic using natural language processing techniques. Third IEEE international conference on data mining.IEEE. Available from: https://ieeexplore.ieee.org/abstract/document/1250949
[18]	Barkur G, Vibha GB (2020) Sentiment analysis of nationwide lockdown due to COVID 19 outbreak: Evidence from India. Asian Journal of Psychiatry 51: 102089. https://doi.org/10.1016/j.ajp.2020.1020890000
[19]	de Las Heras-Pedrosa C, Sánchez-Núñez P, Peláez JI (2020) Sentiment analysis and emotion understanding during the COVID-19 pandemic in Spain and its impact on digital ecosystems. Int J Environ Res Public Health 17: 5542. https://doi.org/10.3390/ijerph17155542
[20]	Government of AlbertaOffice of the Chief Medical Officer of Health (2020). Available from: https://www.alberta.ca/office-of-the-chief-medical-officer-of-health.aspx
[21]	Government of AlbertaCOVID-19 info for Albertans (2020). Available from: https://www.alberta.ca/covid
[22]	Government of AlbertaCOVID-19 Alberta statistics (2020). Available from: https://www.alberta.ca/stats/covid-19-alberta-statistics.htm
[23]	(2021) R Core TeamR: A language and environment for statistical computing. Vienna, Austria: R Foundation for Statistical Computing. Available from: https://www.r-project.org/.
[24]	Wickham H stringr: Simple, consistent wrappers for common string operations (2019). R package version 1.4.0. Available from: https://cran.r-project.org/web/packages/stringr/index.html.
[25]	Silge J, Robinson D (2016) tidytext: Text mining and analysis using tidy data principles in R. JOSS 1: 37. https://doi.org/10.21105/joss.00037
[26]	Mullen AL, Benoit K, Keyes O, et al. (2018) Fast, consistent tokenization of natural language text. JOSS 3: 655. https://doi.org/10.21105/joss.00655
[27]	Rinker TW textstem: Tools for stemming and lemmatizing text (2018). Available from: https://github.com/trinker/textstem
[28]	Hu M, Liu B (2004) Mining and summarizing customer reviews. Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery & Data Mining (KDD-2004).University of Illinois at Chicago. Available from: https://doi.org/10.1145/1014052.1014073
[29]	Mohammad SM, Turney PD (2013) Crowdsourcing a word–emotion association lexicon. Comput Intell-US 29: 436-465. https://doi.org/10.1111/j.1467-8640.2012.00460.x
[30]	Plutchik R (1980) A general psychoevolutionary theory of emotion. Emotion: Theory, research and experience, Theories of emotion. New York: Academic Press: 3-33. https://doi.org/10.1016/B978-0-12-558701-3.50007-7
[31]	Savoia E, Lin L, Viswanath K (2013) Communications in public health emergency preparedness: a systematic review of the literature. Biosecur Bioterror 11: 170-184. https://doi.org/10.1089/bsp.2013.0038
[32]	Tumpey AJ, Daigle D, Nowak G (2018) Communicating during an outbreak or public health investigation. The CDC field epidemiology manual.Oxford University Press. Available from: https://www.cdc.gov/eis/field-epi-manual/index.html
[33]	Leask J, Hooker C (2020) How risk communication could have reduced controversy about school closures in Australia during the COVID-19 pandemic. Public Health Res Pr 30: 3022007. https://doi.org/10.17061/phrp3022007
[34]	Hung L, Lin M (2022) Clear, consistent and credible messages are needed for promoting compliance with COVID-19 public health measures. Evid Based Nurs 25: 22. https://doi.org/10.1136/ebnurs-2020-103358
[35]	Wang T, Lu K, Chow KP, et al. (2020) COVID-19 sensing: negative sentiment analysis on social media in China via BERT model. IEEE Access 8: 138162-138169. https://doi.org/10.1109/ACCESS.2020.3012595
[36]	Aljameel SS, Alabbad DA, Alzahrani NA, et al. (2021) A sentiment analysis approach to predict an individual's awareness of the precautionary procedures to prevent COVID-19 outbreaks in Saudi Arabia. Int J Environ Res Public Health 18: 218. https://doi.org/10.3390/ijerph18010218
[37]	Chen Y, Skiena S (2014) Building sentiment lexicons for all major languages. Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics . https://doi.org/10.3115/v1/P14-2063

Reader Comments

your name:*

Email:*
© 2022 the Author(s), licensee AIMS Press. This is an open access article distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/by/4.0)