Global spatiotemporal trends and determinants of COVID-19 vaccine acceptance on Twitter: a multilingual deep learning study in 135 countries and territories

Zhou, Xinyu; Zhang, Xu; Larson, Heidi J.; Figueiredo, Alexandre de; Jit, Mark; Fodeh, Samah Jamal; Vermund, Sten H.; Zang, Sujie; Lin, Leesa; Hou, Zhiyuan

doi:10.1101/2022.11.14.22282300

Cited by 3 publications

(17 citation statements)

References 33 publications

(46 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Only four studies 19 , 33 , 34 , 43 ( N = 4 ~ 14%) provide data and implementation code for the public. Two research articles 32 , 45 provided the public access link to the implementation code but didn’t provide an access link to the data due to Twitter public policy restrictions.…”

Section: Resultsmentioning

confidence: 99%

“… Monitor vaccine hesitancy https://gitlab.com/covid19aidashboard/covid-vaccination/ https://gitlab.com/covid19aidashboard/covid-vaccination/ 33 7. Public attitude toward vaccination https://github.com/xinyuuzhou/COVID-19-vaccine-on-Twitter https://github.com/xinyuuzhou/COVID-19-vaccine-on-Twitter 34 8. Misinformation processing Data available on request: (Email: iherrpec@uax.es) Code will be provided on request: (Email: iherrpec@uax.es) 37 9.…”

Section: Resultsmentioning

confidence: 99%

“… 19 , 30 , 32 , 33 , 35 , 37 , 38 , 40 , 42 The second highest reported region for longitudinal analysis is the UK and reported in ( N = 8 ~ 29%) research studies. 22 , 23 , 33 , 34 , 38 , 41 , 44 , 46 India and Pakistan reported in retrospective studies 22 , 34 , 38 for users’ behavior analysis toward vaccination. Australia and Brazil reported in ( N = 4 ~ 14%) studies 21 , 22 , 34 , 38 for attitude analysis toward vaccination longitudinally.…”

Section: Resultsmentioning

confidence: 99%

“… 22 , 23 , 33 , 34 , 38 , 41 , 44 , 46 India and Pakistan reported in retrospective studies 22 , 34 , 38 for users’ behavior analysis toward vaccination. Australia and Brazil reported in ( N = 4 ~ 14%) studies 21 , 22 , 34 , 38 for attitude analysis toward vaccination longitudinally.…”

Section: Resultsmentioning

confidence: 99%

“…Only one article 21 reported 1.4 billion tweets for retrospective analysis of user behavior. Similarly, a single article 34 reported about 13 million tweets for behavioral analysis toward vaccination.…”

Section: Resultsmentioning

confidence: 99%

See 4 more Smart Citations

Longitudinal analysis of behavioral factors and techniques used to identify vaccine hesitancy among Twitter users: Scoping review

Khan,

Biswas,

Shah

2023

Human Vaccines & Immunotherapeutics

View full text Add to dashboard Cite

While vaccines have played a pivotal role in the fight against infectious diseases, individuals engage in online resources to find vaccine-related support and information. The benefits and consequences of these online peers are unclear and mainly cause a behavioral shift in user sentiment toward vaccination. This scoping review aims to identify the community and individual factors that longitudinally influence public behavior toward vaccination. The secondary aim is to gain insight into techniques and methodologies used to extract these factors from Twitter data. We followed PRISMA-ScR guidelines to search various online repositories. From this search process, a total of 28 most relevant articles out of 705 relevant studies. Three main themes emerged including individual and community factors influencing public attitude toward vaccination, and techniques employed to identify these factors. Anti-vax, Pro-vax, and neutral are the major communities, while misinformation, vaccine campaign, and user demographics are the common individual factors assessed during this reviewing process. Twitter user sentiment (positive, negative, and neutral) and emotions (fear, trust, sadness) were also discussed to identify the intentions to accept or refuse vaccines. SVM, LDA, BERT are the techniques used for topic modeling, while Louvain, NodeXL, and Infomap algorithms are used for community detection. This research is notable for being the first systematic review that emphasizes the dearth of longitudinal studies and the methodological and underlying practical constraints underpinning the lucrative implementation of an explainable and longitudinal behavior analysis system. Moreover, new possible research directions are suggested for the researchers to perform accurate human behavior analysis.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Resultsmentioning

confidence: 99%

Section: Resultsmentioning

confidence: 99%

Section: Resultsmentioning

confidence: 99%

Section: Resultsmentioning

confidence: 99%

See 3 more Smart Citations

Longitudinal analysis of behavioral factors and techniques used to identify vaccine hesitancy among Twitter users: Scoping review

Khan,

Biswas,

Shah

2023

Human Vaccines & Immunotherapeutics

View full text Add to dashboard Cite

show abstract

Deep Learning Analysis of COVID-19 Vaccine Hesitancy and Confidence Expressed on Twitter in 6 High-Income Countries: Longitudinal Observational Study

Zhou,

Song,

Zhang

et al. 2023

J Med Internet Res

Self Cite

View full text Add to dashboard Cite

Background An ongoing monitoring of national and subnational trajectory of COVID-19 vaccine hesitancy could offer support in designing tailored policies on improving vaccine uptake. Objective We aim to track the temporal and spatial distribution of COVID-19 vaccine hesitancy and confidence expressed on Twitter during the entire pandemic period in major English-speaking countries. Methods We collected 5,257,385 English-language tweets regarding COVID-19 vaccination between January 1, 2020, and June 30, 2022, in 6 countries—the United States, the United Kingdom, Australia, New Zealand, Canada, and Ireland. Transformer-based deep learning models were developed to classify each tweet as intent to accept or reject COVID-19 vaccination and the belief that COVID-19 vaccine is effective or unsafe. Sociodemographic factors associated with COVID-19 vaccine hesitancy and confidence in the United States were analyzed using bivariate and multivariable linear regressions. Results The 6 countries experienced similar evolving trends of COVID-19 vaccine hesitancy and confidence. On average, the prevalence of intent to accept COVID-19 vaccination decreased from 71.38% of 44,944 tweets in March 2020 to 34.85% of 48,167 tweets in June 2022 with fluctuations. The prevalence of believing COVID-19 vaccines to be unsafe continuously rose by 7.49 times from March 2020 (2.84% of 44,944 tweets) to June 2022 (21.27% of 48,167 tweets). COVID-19 vaccine hesitancy and confidence varied by country, vaccine manufacturer, and states within a country. The democrat party and higher vaccine confidence were significantly associated with lower vaccine hesitancy across US states. Conclusions COVID-19 vaccine hesitancy and confidence evolved and were influenced by the development of vaccines and viruses during the pandemic. Large-scale self-generated discourses on social media and deep learning models provide a cost-efficient approach to monitoring routine vaccine hesitancy.

show abstract

Detecting Vaccine Sentiment on Twitter: Concerns and Solutions (Preprint)

Fodeh,

Zhou,

Kedia

et al. 2024

Preprint

View full text Add to dashboard Cite

BACKGROUND The COVID-19 pandemic, ongoing for over three years, has led to significant global impacts, with 1.1 million deaths in the US and 6,180,000 worldwide due to COVID-19. COVID-19 vaccines, introduced in late 2020, have been endorsed by public health authorities worldwide as a vital defense against severe illness and death. Social media platforms, particularly Twitter, offer valuable insights into public opinions and responses regarding COVID-19 vaccination. Many studies have employed machine learning to analyze extensive Twitter data. Sentiment analysis tools like Vader and TextBlob have been extensively used to gauge sentiment towards vaccines, creating reference datasets for text classification models. This research examines the reliability of this approach and introduces an alternative solution based on few-shot learning for building more robust sentiment classification models. OBJECTIVE The goal is to determine the reliability of Vader and TextBlob and assess their suitability for generating robust gold standard datasets for downstream tasks such as sentiment classification compared to standard machine learning-based classifiers as well as advanced pre-trained language models. METHODS We applied Vader and TextBlob to three Twitter-based datasets labeled by humans to obtain the sentiments of the tweets (positive, negative, or neutral). We compared the performance of Vader and TextBlob to traditional machine learning-based sentiment classifiers including Random Forest, Logistic Regression, Stochastic Gradient Descent, Multinomial Naive Bayes, Deep Neural Network (DNN), and few-shot learning-based classifiers. The few-shot learning models are based on pretraining and fine tuning (PET) models including BERT-Base, BERT-large, and CT-BERT. We evaluated performance using F-score, precision, recall and AUC. RESULTS The findings revealed that Vader and TextBlob performed poorly compared to the other methods. This suggests that relying on sentiment tools like Vader and TextBlob to establish gold standards for sentiment classification models may result in inadequate and weak models that perform poorly on new datasets. All classifiers achieved better F1-scores over the different datasets, with 28% and 8% improvement over Vader and TextBlob. The few-shot learning approach excelled, particularly when dealing with smaller datasets, showcasing a minimum 15% F1-Score improvement with just 10% of labeled data. Few-shot learning consistently outperformed the other models across various training sample sizes. The best F1-Scores reached 0.71, 0.63, and 0.78, across the different datasets, when CT-BERT served as the PET model. CONCLUSIONS This study highlights the limitations of sentiment analysis tools like Vader and TextBlob when used to generate gold standard datasets. These tools may not produce robust and reliable models for sentiment classification. The research proposes an alternative approach using few-shot learning, which can achieve equivalent or better performance with minimal labeled data. This approach provides a promising path for improving sentiment classification models in the context of healthcare and other domains where understanding public sentiment is crucial.

show abstract

Global spatiotemporal trends and determinants of COVID-19 vaccine acceptance on Twitter: a multilingual deep learning study in 135 countries and territories

Cited by 3 publications

References 33 publications

Longitudinal analysis of behavioral factors and techniques used to identify vaccine hesitancy among Twitter users: Scoping review

Longitudinal analysis of behavioral factors and techniques used to identify vaccine hesitancy among Twitter users: Scoping review

Deep Learning Analysis of COVID-19 Vaccine Hesitancy and Confidence Expressed on Twitter in 6 High-Income Countries: Longitudinal Observational Study

Detecting Vaccine Sentiment on Twitter: Concerns and Solutions (Preprint)

Contact Info

Product

Resources

About