Cargando…

Examining the Prevailing Negative Sentiments Related to COVID-19 Vaccination: Unsupervised Deep Learning of Twitter Posts over a 16 Month Period

Despite the demonstrated efficacy, safety, and availability of COVID-19 vaccines, efforts in global mass vaccination have been met with widespread scepticism and vaccine hesitancy or refusal. Understanding the reasons for the public’s negative opinions towards COVID-19 vaccination using Twitter may...

Descripción completa

Detalles Bibliográficos
Autores principales: Ng, Qin Xiang, Lim, Shu Rong, Yau, Chun En, Liew, Tau Ming
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2022
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9503543/
https://www.ncbi.nlm.nih.gov/pubmed/36146535
http://dx.doi.org/10.3390/vaccines10091457
_version_ 1784795989592244224
author Ng, Qin Xiang
Lim, Shu Rong
Yau, Chun En
Liew, Tau Ming
author_facet Ng, Qin Xiang
Lim, Shu Rong
Yau, Chun En
Liew, Tau Ming
author_sort Ng, Qin Xiang
collection PubMed
description Despite the demonstrated efficacy, safety, and availability of COVID-19 vaccines, efforts in global mass vaccination have been met with widespread scepticism and vaccine hesitancy or refusal. Understanding the reasons for the public’s negative opinions towards COVID-19 vaccination using Twitter may help make new headways in improving vaccine uptake. This study, therefore, examined the prevailing negative sentiments towards COVID-19 vaccination via the analysis of public twitter posts over a 16 month period. Original tweets (in English) from 1 April 2021 to 1 August 2022 were extracted. A bidirectional encoder representations from transformers (BERT)-based model was applied, and only negative sentiments tweets were selected. Topic modelling was used, followed by manual thematic analysis performed iteratively by the study investigators, with independent reviews of the topic labels and themes. A total of 4,448,314 tweets were analysed. The analysis generated six topics and three themes related to the prevailing negative sentiments towards COVID-19 vaccination. The themes could be broadly understood as either emotional reactions to perceived invidious policies or safety and effectiveness concerns related to the COVID-19 vaccines. The themes uncovered in the present infodemiology study fit well into the increasing vaccination model, and they highlight important public conversations to be had and potential avenues for future policy intervention and campaign efforts.
format Online
Article
Text
id pubmed-9503543
institution National Center for Biotechnology Information
language English
publishDate 2022
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-95035432022-09-24 Examining the Prevailing Negative Sentiments Related to COVID-19 Vaccination: Unsupervised Deep Learning of Twitter Posts over a 16 Month Period Ng, Qin Xiang Lim, Shu Rong Yau, Chun En Liew, Tau Ming Vaccines (Basel) Article Despite the demonstrated efficacy, safety, and availability of COVID-19 vaccines, efforts in global mass vaccination have been met with widespread scepticism and vaccine hesitancy or refusal. Understanding the reasons for the public’s negative opinions towards COVID-19 vaccination using Twitter may help make new headways in improving vaccine uptake. This study, therefore, examined the prevailing negative sentiments towards COVID-19 vaccination via the analysis of public twitter posts over a 16 month period. Original tweets (in English) from 1 April 2021 to 1 August 2022 were extracted. A bidirectional encoder representations from transformers (BERT)-based model was applied, and only negative sentiments tweets were selected. Topic modelling was used, followed by manual thematic analysis performed iteratively by the study investigators, with independent reviews of the topic labels and themes. A total of 4,448,314 tweets were analysed. The analysis generated six topics and three themes related to the prevailing negative sentiments towards COVID-19 vaccination. The themes could be broadly understood as either emotional reactions to perceived invidious policies or safety and effectiveness concerns related to the COVID-19 vaccines. The themes uncovered in the present infodemiology study fit well into the increasing vaccination model, and they highlight important public conversations to be had and potential avenues for future policy intervention and campaign efforts. MDPI 2022-09-02 /pmc/articles/PMC9503543/ /pubmed/36146535 http://dx.doi.org/10.3390/vaccines10091457 Text en © 2022 by the authors. https://creativecommons.org/licenses/by/4.0/Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
spellingShingle Article
Ng, Qin Xiang
Lim, Shu Rong
Yau, Chun En
Liew, Tau Ming
Examining the Prevailing Negative Sentiments Related to COVID-19 Vaccination: Unsupervised Deep Learning of Twitter Posts over a 16 Month Period
title Examining the Prevailing Negative Sentiments Related to COVID-19 Vaccination: Unsupervised Deep Learning of Twitter Posts over a 16 Month Period
title_full Examining the Prevailing Negative Sentiments Related to COVID-19 Vaccination: Unsupervised Deep Learning of Twitter Posts over a 16 Month Period
title_fullStr Examining the Prevailing Negative Sentiments Related to COVID-19 Vaccination: Unsupervised Deep Learning of Twitter Posts over a 16 Month Period
title_full_unstemmed Examining the Prevailing Negative Sentiments Related to COVID-19 Vaccination: Unsupervised Deep Learning of Twitter Posts over a 16 Month Period
title_short Examining the Prevailing Negative Sentiments Related to COVID-19 Vaccination: Unsupervised Deep Learning of Twitter Posts over a 16 Month Period
title_sort examining the prevailing negative sentiments related to covid-19 vaccination: unsupervised deep learning of twitter posts over a 16 month period
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9503543/
https://www.ncbi.nlm.nih.gov/pubmed/36146535
http://dx.doi.org/10.3390/vaccines10091457
work_keys_str_mv AT ngqinxiang examiningtheprevailingnegativesentimentsrelatedtocovid19vaccinationunsuperviseddeeplearningoftwitterpostsovera16monthperiod
AT limshurong examiningtheprevailingnegativesentimentsrelatedtocovid19vaccinationunsuperviseddeeplearningoftwitterpostsovera16monthperiod
AT yauchunen examiningtheprevailingnegativesentimentsrelatedtocovid19vaccinationunsuperviseddeeplearningoftwitterpostsovera16monthperiod
AT liewtauming examiningtheprevailingnegativesentimentsrelatedtocovid19vaccinationunsuperviseddeeplearningoftwitterpostsovera16monthperiod