Methods for Social Media Monitoring Related to Vaccination: Systematic Scoping Review

A Snapshot of COVID-19 Vaccine Discourse Related to Ethnic Minority Communities in the United Kingdom Between January and April 2022: Mixed Methods Analysis

BACKGROUND

Existing literature highlights the role of social media as a key source of information for the public during the COVID-19 pandemic and its influence on vaccination attempts. Yet there is little research exploring its role in the public discourse specifically among ethnic minority communities, who have the highest rates of vaccine hesitancy (delay or refusal of vaccination despite availability of services).

OBJECTIVE

This study aims to understand the discourse related to minority communities on social media platforms Twitter and YouTube.

METHODS

Social media data from the United Kingdom was extracted from Twitter and YouTube using the software Netlytics and YouTube Data Tools to provide a "snapshot" of the discourse between January and April 2022. A mixed method approach was used where qualitative data were contextualized into codes. Network analysis was applied to provide insight into the most frequent and weighted keywords and topics of conversations.

RESULTS

A total of 260 tweets and 156 comments from 4 YouTube videos were included in our analysis. Our data suggests that the most popular topics of conversation during the period sampled were related to communication strategies adopted during the booster vaccine rollout. These were noted to be divisive in nature and linked to wider conversations around racism and historical mistrust toward institutions.

CONCLUSIONS

Our study suggests a shift in narrative from concerns about the COVID-19 vaccine itself, toward the strategies used in vaccination implementation, in particular the targeting of ethnic minority groups through vaccination campaigns. The implications for public health communication during crisis management in a pandemic context include acknowledging wider experiences of discrimination when addressing ethnic minority communities.

Spatiotemporal trends in COVID-19 vaccine sentiments on a social media platform and correlations with reported vaccine coverage

Objective

To assess spatiotemporal trends in, and determinants of, the acceptance of coronavirus disease 2019 (COVID-19) vaccination globally, as expressed on the social media platform X (formerly Twitter).

Methods

We collected over 13 million posts on the platform regarding COVID-19 vaccination made between November 2020 and March 2022 in 90 languages. Multilingual deep learning XLM-RoBERTa models annotated all posts using an annotation framework after being fine-tuned on 8125 manually annotated, English-language posts. The annotation results were used to assess spatiotemporal trends in COVID-19 vaccine acceptance and confidence as expressed by platform users in 135 countries and territories. We identified associations between spatiotemporal trends in vaccine acceptance and country-level characteristics and public policies by using univariate and multivariate regression analysis.

Findings

A greater proportion of platform users in the World Health Organization's South-East Asia, Eastern Mediterranean and Western Pacific Regions expressed vaccine acceptance than users in the rest of the world. Countries in which a greater proportion of platform users expressed vaccine acceptance had higher COVID-19 vaccine coverage rates. Trust in government was also associated with greater vaccine acceptance. Internationally, vaccine acceptance and confidence declined among platform users as: (i) vaccination eligibility was extended to adolescents; (ii) vaccine supplies became sufficient; (iii) nonpharmaceutical interventions were relaxed; and (iv) global reports on adverse events following vaccination appeared.

Conclusion

Social media listening could provide an effective and expeditious means of informing public health policies during pandemics, and could supplement existing public health surveillance approaches in addressing global health issues.

Online on the frontline: A longitudinal social media analysis of UK healthcare workers' attitudes to COVID-19 vaccines using the 5C framework

This paper explores vaccine hesitancy among healthcare workers (HCWs) in the UK, where different COVID-19 vaccines were being rolled out through a national vaccination campaign from 2020 to 2022, consisting of a first and second dose programme. Through a mixed-method approach using qualitative discourse analysis and network analysis of Twitter data, we assessed HCW perceptions and views about the administration and delivery of COVID-19 vaccines in the United Kingdom (UK). We were also interested in exploring HCWs' personal experiences and attitudes towards taking COVID-19 vaccines themselves. We drew upon sociology, ethics, communication studies and used research methods concentrating on social media and media analysis. By employing the '5C framework' of 'confidence, complacency, constraints, calculation, and collective responsibility' we evaluated a longitudinal selection of tweets to capture relevant factors driving vaccination views and behaviours among HCWs. We found differing positions expressed about COVID-19 vaccines and policy during the first dose compared with the second, through a drop in confidence compounded by supply and access issues, as well the news of a vaccine mandate for HCWs by the UK government in 2021. HCWs asked calculation questions to the community or brought forward competing pieces of information about vaccine policy and guidelines. Constraint levels in access issues were noted, especially for those with work and caregiving responsibilities, and student nurses found they did not have equal vaccination access. HCWs also displayed collective responsibility on social platforms to both encourage vaccination and express concerns through the organisation of social action against vaccine mandates.

Oral rehydration solution (ORS) for fasting doping: Examining the Twitter data in Indonesia

Oral rehydration solution (ORS) or oralit is a sugar and salt-based solution that restores electrolyte balance, counters dehydration and mitigates metabolic acidosis. In Indonesia, particularly during the month of Ramadan, the use of ORS as a form of fasting doping has become increasingly prevalent. This study aimed to analyze the patterns of communication, key influencers, and sentiment within the Twitter network in Indonesia regarding the use of ORS as fasting doping. From March 15 to March 26, 2023, Twitter data was collected using NodeXL software. The dataset was then analyzed using NodeXL and Gephi software to identify key influencers and patterns within the network. To assess attitudes towards the use of ORS as fasting doping expressed in tweets, sentiment analysis was conducted using Azure Machine. The dataset consisted of 13,746 tweets, from which the analysis revealed that Twitter discourse concerning the use of ORS as fasting doping demonstrated a diverse range of individuals. The top five users with the highest betweenness centrality scores were medical doctors, mention and confess (menfess) accounts, and personal accounts. The sentiment analysis of the collected tweets unveiled a relatively high negative sentiment toward the use of ORS for fasting purposes. Notably, the proportion of positive and neutral sentiments were comparable. Our data indicate that ORS use as fasting doping is controversial in Indonesia. Most tweets express concerns about misuse and negative consequences, indicating a need for guidance and regulation from public health authorities. Further research and guidelines are necessary to ensure the safe and appropriate use.

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

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.

Spreading of misinformation on mass media and digital platforms regarding vaccines. A systematic scoping review on stakeholders, policymakers, and sentiments/behavior of Italian consumers

Studies on traditional and social media have found that misinformation about vaccines has been widely spread over the last decade, negatively impacting public opinion and people's willingness to get vaccinated. We reviewed the sentiments of Italian users to define the characteristic of anti-vax and pro-vax contents and defined the strategies to deal with the misinformation. Scopus, MEDLINE/PubMed, Google Scholar (up to page 10), and ISI Web of Knowledge databases were systematically searched. Research articles, brief reports, commentaries, and letters published between January 1, 2010 and March 30, 2022 were included in the search. No-vax or ambiguous contents in Italian mass media are not prevalent compared to neutral and pro-vax content; the communication of no-vax groups is significantly simplified, favoring the understanding of the topics by users. Events related to vaccinations are associated with news coverage by media, search engine consultations, and user reactions on social networks. In this context, the activity of no-vax groups is triggered, and misinformation and fake news spread even further. A multifactorial approach is necessary to manage online user sentiment and use mass and social media as health promotion tools.

So Many Choices, How Do I Choose? Considerations for Selecting Digital Health Interventions to Support Immunization Confidence and Demand

Childhood vaccines are a safe, effective, and essential component of any comprehensive public health system. Successful and complete child immunization requires sensitivity and responsiveness to community needs and concerns while reducing barriers to access and providing respectful quality services. Community demand for immunization is influenced by multiple complex factors, involving attitudes, trust, and the dynamic relationship between caregivers and health workers. Digital health interventions have the potential to help reduce barriers and enhance opportunities for immunization access, uptake, and demand in low- and middle-income countries. But with limited evidence and many interventions to choose from, how do decision makers identify promising and appropriate tools? Early evidence and experiences with digital health interventions for immunization demand are presented in this viewpoint to help stakeholders make decisions, guide investment, coordinate efforts, as well as design and implement digital health interventions to support vaccine confidence and demand.

Exploring the vaccine conversation on TikTok in Italy: beyond classic vaccine stances

TikTok, a social media platform for creating and sharing short videos, has seen a surge in popularity during the COVID-19 pandemic. To analyse the Italian vaccine conversation on TikTok, we downloaded a sample of videos with a high play count (Top Videos), identified through an unofficial Application Programming Interface (consistent with TikTok's Terms of Service), and collected public videos from vaccine sceptic users through snowball sampling (Vaccine Sceptics' videos). The videos were analysed using qualitative and quantitative methods, in terms of vaccine stance, tone of voice, topic, conformity with TikTok style, and other characteristics. The final datasets consisted of 754 Top Videos (by 510 single users) plus 180 Vaccine Sceptics' videos (by 29 single users), posted between January 2020 and March 2021. In 40.5% of the Top Videos the stance was promotional, 33.9% were indefinite-ironic, 11.3% were neutral, 9.7% were discouraging, and 3.1% were ambiguous (i.e. expressing an ambivalent stance towards vaccines); 43% of promotional videos were from healthcare professionals. More than 95% of the Vaccine Sceptic videos were discouraging. Multiple correspondence analysis showed that, compared to other stances, promotional videos were more frequently created by healthcare professionals and by females, and their most frequent topic was herd immunity. Discouraging videos were associated with a polemical tone of voice and their topics were conspiracy and freedom of choice. Our analysis shows that Italian vaccine-sceptic users on TikTok are limited in number and vocality, and the large proportion of videos with an indefinite-ironic stance might imply that the incidence of affective polarisation could be lower on TikTok, compared to other social media, in the Italian context. Safety is the most frequent concern of users, and we recorded an interesting presence of healthcare professionals among the creators. TikTok should be considered as a medium for vaccine communication and for vaccine promotion campaigns.

Reasons for not getting COVID-19 vaccine in Ardabil, a Northwestern province in Iran: Based on an ecological approach

BACKGROUND

Understanding the reasons for not getting the COVID-19 vaccine can help to increase acceptability and tackle vaccine hesitancy and consequently reach high coverage for this new vaccine. Using an ecological approach, the reasons for not getting the vaccine in the Iranian population was investigated.

METHODS AND MATERIAL

This study was conducted from October to December 2021 on 426 participants who had not received the COVID-19 vaccine. The following subsets of questions were included in the questionnaire: intrapersonal level factors, interpersonal level factors, group and organization, and society and policy-making. Multivariable logistic regression was used, and the odds ratio (OR) and 95% confidence intervals (CIs) were estimated for vaccine hesitancy (dependent variable) according to the reasons for not getting COVID vaccine scores (independent variable) using multivariable logistic regression in 3 different models, including Model 0: unadjusted, Model 1: adjusted for age, gender, and underlying disease, and Model 2: adjustment for age, gender, underlying disease, education, place of living, income, marital status, and employment.

RESULTS

A significant difference was found regarding gender between likely and not likely groups (P = 0.016). A significant association was observed between the vaccine hesitancy and interpersonal (unadjusted model: OR = 0.833 (CI: 0.738-0.942), P for trend = 0.003; model 1: OR = 0.820 (CI: 0.724-0.930), P for trend = 0.002; model 2: OR = 0.799 (CI: 0.703-0.909), P for trend = 0.001) and group and organization (unadjusted model: OR = 0.861 (CI: 0.783-0.948), P for trend = 0.002; model 1: OR = 0.864 (CI: 0.784-0.952, P for trend = 0.003; model 2:OR = 0.862 (CI: 0.781-0.951, P for trend = 0.003). There was no significant association between vaccine hesitancy and intrapersonal and society and policy-making (P > 0.05).

CONCLUSIONS

We found that a high score of "interpersonal" and "group and organization" factors were associated with lower intention to COVID vaccine. Moreover, women had higher vaccination intentions than men.

Content and sentiment surveillance (CSI): A critical component for modeling modern epidemics

Comprehensive surveillance systems are the key to provide accurate data for effective modeling. Traditional symptom-based case surveillance has been joined with recent genomic, serologic, and environment surveillance to provide more integrated disease surveillance systems. A major gap in comprehensive disease surveillance is to accurately monitor potential population behavioral changes in real-time. Population-wide behaviors such as compliance with various interventions and vaccination acceptance significantly influence and drive the overall epidemic dynamics in the society. Original infoveillance utilizes online query data (e.g., Google and Wikipedia search of a specific content topic such as an epidemic) and later focuses on large volumes of online discourse data about the from social media platforms and further augments epidemic modeling. It mainly uses number of posts to approximate public awareness of the disease, and further compares with observed epidemic dynamics for better projection. The current COVID-19 pandemic shows that there is an urgency to further harness the rich, detailed content and sentiment information, which can provide more accurate and granular information on public awareness and perceptions toward multiple aspects of the disease, especially various interventions. In this perspective paper, we describe a novel conceptual analytical framework of content and sentiment infoveillance (CSI) and integration with epidemic modeling. This CSI framework includes data retrieval and pre-processing; information extraction via natural language processing to identify and quantify detailed time, location, content, and sentiment information; and integrating infoveillance with common epidemic modeling techniques of both mechanistic and data-driven methods. CSI complements and significantly enhances current epidemic models for more informed decision by integrating behavioral aspects from detailed, instantaneous infoveillance from massive social media data.

Attitudes of Swedish Language Twitter Users Toward COVID-19 Vaccination: Exploratory Qualitative Study

Background

Social media have played an important role in shaping COVID-19 vaccine choices during the pandemic. Understanding people’s attitudes toward the vaccine as expressed on social media can help address the concerns of vaccine-hesitant individuals.

Objective

The aim of this study was to understand the attitudes of Swedish-speaking Twitter users toward COVID-19 vaccines.

Methods

This was an exploratory qualitative study that used a social media–listening approach. Between January and March 2022, a total of 2877 publicly available tweets in Swedish were systematically extracted from Twitter. A deductive thematic analysis was conducted using the World Health Organization’s 3C model (confidence, complacency, and convenience).

Results

Confidence in the safety and effectiveness of the COVID-19 vaccine appeared to be a major concern expressed on Twitter. Unclear governmental strategies in managing the pandemic in Sweden and the belief in conspiracy theories have further influenced negative attitudes toward vaccines. Complacency—the perceived risk of COVID-19 was low and booster vaccination was unnecessary; many expressed trust in natural immunity. Convenience—in terms of accessing the right information and the vaccine—highlighted a knowledge gap about the benefits and necessity of the vaccine, as well as complaints about the quality of vaccination services.

Conclusions

Swedish-speaking Twitter users in this study had negative attitudes toward COVID-19 vaccines, particularly booster vaccines. We identified attitudes toward vaccines and misinformation, indicating that social media monitoring can help policy makers respond by developing proactive health communication interventions.

Australasian Institute of Digital Health Summit 2022-Automated Social Media Surveillance for Detection of Vaccine Safety Signals: A Validation Study

BACKGROUND

Social media platforms have emerged as a valuable data source for public health research and surveillance. Monitoring of social media and user-generated data on the Web enables timely and inexpensive collection of information, overcoming time lag and cost of traditional health reporting systems.

OBJECTIVES

This article identifies personally experienced coronavirus disease 2019 (COVID-19) vaccine reactions expressed on Twitter and validate the findings against an established vaccine reactions reporting system.

METHODS

We collected around 3 million tweets from 1.4 million users between February 1, 2021, to January 31, 2022, using COVID-19 vaccines and vaccine reactions keyword lists. We performed topic modeling on a sample of the data and applied a modified F1 scoring technique to identify a topic that best differentiated vaccine-related personal health mentions. We then manually annotated 4,000 of the records from this topic, which were used to train a transformer-based classifier to identify likely personally experienced vaccine reactions. Applying the trained classifier to the entire data set allowed us to select records we could use to quantify potential vaccine side effects. Adverse events following immunization (AEFI) referred to in these records were compared with those reported to the state of Victoria's spontaneous vaccine safety surveillance system, SAEFVIC (Surveillance of Adverse Events Following Vaccination In the Community).

RESULTS

The most frequently mentioned potential vaccine reactions generally aligned with SAEFVIC data. Notable exceptions were increased Twitter reporting of bleeding-related AEFI and allergic reactions, and more frequent SAEFVIC reporting of cardiac AEFI.

CONCLUSION

Social media conversations are a potentially valuable supplementary data source for detecting vaccine adverse event mentions. Monitoring of online observations about new vaccine-related personal health experiences has the capacity to provide early warnings about emerging vaccine safety issues.

Tick-Talk: Parental online discourse about TBE vaccination

This study aimed to understand parental discourse about vaccination, and to provide guidance for communication that addresses the needs of parents. We analyzed parental discourse on child vaccination in general and tick-borne encephalitis (TBE) specifically in a Swiss parental online community. For this purpose, a data set containing 105k posts written by parents between 2007 and 2019 was analyzed using a combination of linguistic discourse analysis and qualitative content analysis. Results show that parents enter into a multidimensional decision-making process, characterized by elaborate practices of negotiation, consideration of vaccination recommendations as well as six distinct influencing thematic factors (vaccination safety, development and control, effectiveness, epidemiology, necessity, alternatives or additional prevention methods). The study shows a clear pattern of seasonality, with parents talking about TBE vaccination mostly triggered by events such as tick bites in spring and summer. From a public health perspective, the study emphasizes the need for sufficient, balanced, and tailored information about TBE vaccination. Online forums provide valuable information about what matters to parents and when, which can help public health authorities and practitioners provide information according to these concerns and enhance health literacy among parents.

Effectiveness of Social Video Platforms in Promoting COVID-19 Vaccination Among Youth: A Content-Specific Analysis of COVID-19 Vaccination Topic Videos on Bilibili

Background

With the widespread promotion of the COVID-19 vaccination in China, videos about the vaccination have become increasingly available on social video platforms. With the User Generated Content model, different creators’ interpretations of COVID-19 vaccines may influence the attitudes towards the vaccines and vaccination.

Objective

To explore the overview of COVID-19 vaccine-related videos on Bilibili, discussing the communication effects of COVID-19 topic videos and its influencing factors.

Methods

A content analysis was applied to the 202 video samples obtained through data mining regarding the creator’s information, video presentation, and COVID-19 vaccine-related content.

Results

Individuals and medical professionals preferred VLOG videos, media chose to upload informational videos, and enterprises preferred to post showcase videos. Individuals were more likely to discuss the adverse reactions in their videos, while medical professionals were more likely to discuss the vaccination process for the COVID-19 vaccine. Videos with core issues positively influenced the video’s dissemination breadth. The attitudes toward the COVID-19 vaccine in the videos positively influence the recognition of the videos. The richness of knowledge points related to the COVID-19 vaccine negatively affected the recognition and participation.

Conclusion

Social video platforms could play an active role in the vaccination promotion for the youth. Health promotion-related departments and individuals could strengthen agenda setting, grasp the characteristics of young groups, and express positive attitudes toward health issues to achieve better health (vaccine) promotion.

Understanding the vaccine stance of Italian tweets and addressing language changes through the COVID-19 pandemic: Development and validation of a machine learning model

Social media is increasingly being used to express opinions and attitudes toward vaccines. The vaccine stance of social media posts can be classified in almost real-time using machine learning. We describe the use of a Transformer-based machine learning model for analyzing vaccine stance of Italian tweets, and demonstrate the need to address changes over time in vaccine-related language, through periodic model retraining. Vaccine-related tweets were collected through a platform developed for the European Joint Action on Vaccination. Two datasets were collected, the first between November 2019 and June 2020, the second from April to September 2021. The tweets were manually categorized by three independent annotators. After cleaning, the total dataset consisted of 1,736 tweets with 3 categories (promotional, neutral, and discouraging). The manually classified tweets were used to train and test various machine learning models. The model that classified the data most similarly to humans was XLM-Roberta-large, a multilingual version of the Transformer-based model RoBERTa. The model hyper-parameters were tuned and then the model ran five times. The fine-tuned model with the best F-score over the validation dataset was selected. Running the selected fine-tuned model on just the first test dataset resulted in an accuracy of 72.8% (F-score 0.713). Using this model on the second test dataset resulted in a 10% drop in accuracy to 62.1% (F-score 0.617), indicating that the model recognized a difference in language between the datasets. On the combined test datasets the accuracy was 70.1% (F-score 0.689). Retraining the model using data from the first and second datasets increased the accuracy over the second test dataset to 71.3% (F-score 0.713), a 9% improvement from when using just the first dataset for training. The accuracy over the first test dataset remained the same at 72.8% (F-score 0.721). The accuracy over the combined test datasets was then 72.4% (F-score 0.720), a 2% improvement. Through fine-tuning a machine-learning model on task-specific data, the accuracy achieved in categorizing tweets was close to that expected by a single human annotator. Regular training of machine-learning models with recent data is advisable to maximize accuracy.

Media Data and Vaccine Hesitancy: Scoping Review

Background

Media studies are important for vaccine hesitancy research, as they analyze how the media shapes risk perceptions and vaccine uptake. Despite the growth in studies in this field owing to advances in computing and language processing and an expanding social media landscape, no study has consolidated the methodological approaches used to study vaccine hesitancy. Synthesizing this information can better structure and set a precedent for this growing subfield of digital epidemiology.

Objective

This review aimed to identify and illustrate the media platforms and methods used to study vaccine hesitancy and how they build or contribute to the study of the media's influence on vaccine hesitancy and public health.

Methods

This study followed the PRISMA-ScR (Preferred Reporting Items for Systematic Reviews and Meta-Analyses extension for Scoping Reviews) guidelines. A search was conducted on PubMed and Scopus for any studies that used media data (social media or traditional media), had an outcome related to vaccine sentiment (opinion, uptake, hesitancy, acceptance, or stance), were written in English, and were published after 2010. Studies were screened by only 1 reviewer and extracted for media platform, analysis method, the theoretical models used, and outcomes.

Results

In total, 125 studies were included, of which 71 (56.8%) used traditional research methods and 54 (43.2%) used computational methods. Of the traditional methods, most used content analysis (43/71, 61%) and sentiment analysis (21/71, 30%) to analyze the texts. The most common platforms were newspapers, print media, and web-based news. The computational methods mostly used sentiment analysis (31/54, 57%), topic modeling (18/54, 33%), and network analysis (17/54, 31%). Fewer studies used projections (2/54, 4%) and feature extraction (1/54, 2%). The most common platforms were Twitter and Facebook. Theoretically, most studies were weak. The following five major categories of studies arose: antivaccination themes centered on the distrust of institutions, civil liberties, misinformation, conspiracy theories, and vaccine-specific concerns; provaccination themes centered on ensuring vaccine safety using scientific literature; framing being important and health professionals and personal stories having the largest impact on shaping vaccine opinion; the coverage of vaccination-related data mostly identifying negative vaccine content and revealing deeply fractured vaccine communities and echo chambers; and the public reacting to and focusing on certain signals-in particular cases, deaths, and scandals-which suggests a more volatile period for the spread of information.

Conclusions

The heterogeneity in the use of media to study vaccines can be better consolidated through theoretical grounding. Areas of suggested research include understanding how trust in institutions is associated with vaccine uptake, how misinformation and information signaling influence vaccine uptake, and the evaluation of government communications on vaccine rollouts and vaccine-related events. The review ends with a statement that media data analyses, though groundbreaking in approach, should supplement-not supplant-current practices in public health research.

COVID-19 vaccine hesitancy: a social media analysis using deep learning

Hesitant attitudes have been a significant issue since the development of the first vaccines-the WHO sees them as one of the most critical global health threats. The increasing use of social media to spread questionable information about vaccination strongly impacts the population's decision to get vaccinated. Developing text classification methods that can identify hesitant messages on social media could be useful for health campaigns in their efforts to address negative influences from social media platforms and provide reliable information to support their strategies against hesitant-vaccination sentiments. This study aims to evaluate the performance of different machine learning models and deep learning methods in identifying vaccine-hesitant tweets that are being published during the COVID-19 pandemic. Our concluding remarks are that Long Short-Term Memory and Recurrent Neural Network models have outperformed traditional machine learning models on detecting vaccine-hesitant messages in social media, with an accuracy rate of 86% against 83%.

Public reactions towards Covid-19 vaccination through twitter before and after second wave in India

Social media have a significant impact on opinion building in public. Vaccination in India started in January 2021. We have seen many opinions towards vaccination of the people, as vaccination is one of the most crucial steps toward the fight against COVID-19. In this paper, we have compared the public’s sentiments towards COVID vaccination in India before the second wave and after the second wave. We worked by extracting tweets regarding vaccination in India, building our datasets. We extracted 5977 tweets before the second wave and 42,936 tweets after the second wave. We annotated the collected tweets into four categories, namely Provaccine, Antivaccine, Hesitant and Cognizant. We built a baseline model for sentiment analysis and have used multiple classification techniques among which Random Forest using the TF-IDF vectorization technique gave the best accuracy of 69% using max-features and n-estimators as parameters.

Monitoring user opinions and side effects on COVID-19 vaccines in the Twittersphere: Infodemiology Study of Tweets

Background

In the current phase of the COVID-19 pandemic, we are witnessing the most massive vaccine rollout in human history. Like any other drug, vaccines may cause unexpected side effects, which need to be investigated in a timely manner to minimize harm in the population. If not properly dealt with, side effects may also impact public trust in the vaccination campaigns carried out by national governments.

Objective

Monitoring social media for the early identification of side effects, and understanding the public opinion on the vaccines are of paramount importance to ensure a successful and harmless rollout. The objective of this study was to create a web portal to monitor the opinion of social media users on COVID-19 vaccines, which can offer a tool for journalists, scientists, and users alike to visualize how the general public is reacting to the vaccination campaign.

Methods

We developed a tool to analyze the public opinion on COVID-19 vaccines from Twitter, exploiting, among other techniques, a state-of-the-art system for the identification of adverse drug events on social media; natural language processing models for sentiment analysis; statistical tools; and open-source databases to visualize the trending hashtags, news articles, and their factuality. All modules of the system are displayed through an open web portal.

Results

A set of 650,000 tweets was collected and analyzed in an ongoing process that was initiated in December 2020. The results of the analysis are made public on a web portal (updated daily), together with the processing tools and data. The data provide insights on public opinion about the vaccines and its change over time. For example, users show a high tendency to only share news from reliable sources when discussing COVID-19 vaccines (98% of the shared URLs). The general sentiment of Twitter users toward the vaccines is negative/neutral; however, the system is able to record fluctuations in the attitude toward specific vaccines in correspondence with specific events (eg, news about new outbreaks). The data also show how news coverage had a high impact on the set of discussed topics. To further investigate this point, we performed a more in-depth analysis of the data regarding the AstraZeneca vaccine. We observed how media coverage of blood clot–related side effects suddenly shifted the topic of public discussions regarding both the AstraZeneca and other vaccines. This became particularly evident when visualizing the most frequently discussed symptoms for the vaccines and comparing them month by month.

Conclusions

We present a tool connected with a web portal to monitor and display some key aspects of the public’s reaction to COVID-19 vaccines. The system also provides an overview of the opinions of the Twittersphere through graphic representations, offering a tool for the extraction of suspected adverse events from tweets with a deep learning model.

The dramatic increase in anti-vaccine discourses during the COVID-19 pandemic: a social network analysis of Twitter

Background/Aim

The first case of COVID-19 in Turkey was officially recorded on March 11, 2020. Social media use increased worldwide, as well as in Turkey, during the pandemic, and conspiracy theories/fake news about medical complications of vaccines spread throughout the world. The aim of this study was to identify community interactions related to vaccines and to identify key influences/influencers before and after the pandemic using social network data from Twitter.

Materials and methods

Two datasets, including tweets about vaccinations before and after COVID-19 in Turkey, were collected. Social networks were created based on interactions (mentions) between Twitter users. Users and their influence were scored based on social network analysis and parameters that included in-degree and betweenness centrality.

Results

In the pre-COVID-19 network, media figures and authors who had anti-vaccine views were the most influential users. In the post-COVID-19 network, the Turkish minister of health, the was the most influential figure. The vaccine network was observed to be growing rapidly after COVID-19, and the physicians and authors who had opinions about mandatory vaccinations received a great deal of reaction. One-way communication between influencers and other users in the network was determined.

Conclusions

This study shows the effectiveness and usefulness of large social media data for understanding public opinion on public health and vaccination in Turkey. The current study was completed before the implementation of the COVID-19 vaccine in Turkey. We anticipated that social network analysis would help reduce the “infodemic” before administering the vaccine and would also help public health workers act more proactively in this regard.

Content and Dynamics of Websites Shared Over Vaccine-Related Tweets in COVID-19 Conversations: Computational Analysis

BACKGROUND

The onset of the COVID-19 pandemic and the consequent "infodemic" increased concerns about Twitter's role in advancing antivaccination messages, even before a vaccine became available to the public. New computational methods allow for analysis of cross-platform use by tracking links to websites shared over Twitter, which, in turn, can uncover some of the content and dynamics of information sources and agenda-setting processes. Such understanding can advance theory and efforts to reduce misinformation.

OBJECTIVE

Informed by agenda-setting theory, this study aimed to identify the content and temporal patterns of websites shared in vaccine-related tweets posted to COVID-19 conversations on Twitter between February and June 2020.

METHODS

We used triangulation of data analysis methods. Data mining consisted of the screening of around 5 million tweets posted to COVID-19 conversations to identify tweets that related to vaccination and including links to websites shared within these tweets. We further analyzed the content the 20 most-shared external websites using a mixed methods approach.

RESULTS

Of 841,896 vaccination-related tweets identified, 185,994 (22.1%) contained links to specific websites. A wide range of websites were shared, with the 20 most-tweeted websites constituting 14.5% (27,060/185,994) of the shared websites and typically being shared for only 2 to 3 days. Traditional media constituted the majority of these 20 websites, along with other social media and governmental sources. We identified markers of inauthentic propagation for some of these links.

CONCLUSIONS

The topic of vaccination was prevalent in tweets about COVID-19 early in the pandemic. Sharing websites was a common communication strategy, and its "bursty" pattern and inauthentic propagation strategies pose challenges for health promotion efforts. Future studies should consider cross-platform use in dissemination of health information and in counteracting misinformation.

Multi-perspectives systematic review on the applications of sentiment analysis for vaccine hesitancy

A substantial impediment to widespread Coronavirus disease (COVID-19) vaccination is vaccine hesitancy. Many researchers across scientific disciplines have presented countless studies in favor of COVID-19 vaccination, but misinformation on social media could hinder vaccination efforts and increase vaccine hesitancy. Nevertheless, studying people's perceptions on social media to understand their sentiment presents a powerful medium for researchers to identify the causes of vaccine hesitancy and therefore develop appropriate public health messages and interventions. To the best of the authors' knowledge, previous studies have presented vaccine hesitancy in specific cases or within one scientific discipline (i.e., social, medical, and technological). No previous study has presented findings via sentiment analysis for multiple scientific disciplines as follows: (1) social, (2) medical, public health, and (3) technology sciences. Therefore, this research aimed to review and analyze articles related to different vaccine hesitancy cases in the last 11 years and understand the application of sentiment analysis on the most important literature findings. Articles were systematically searched in Web of Science, Scopus, PubMed, IEEEXplore, ScienceDirect, and Ovid from January 1, 2010, to July 2021. A total of 30 articles were selected on the basis of inclusion and exclusion criteria. These articles were formed into a taxonomy of literature, along with challenges, motivations, and recommendations for social, medical, and public health and technology sciences. Significant patterns were identified, and opportunities were promoted towards the understanding of this phenomenon.

Mild Adverse Events of Sputnik V Vaccine in Russia: Social Media Content Analysis of Telegram via Deep Learning

Background

There is a limited amount of data on the safety profile of the COVID-19 vector vaccine Gam-COVID-Vac (Sputnik V). Previous infodemiology studies showed that social media discourse could be analyzed to assess the most concerning adverse events (AE) caused by drugs.

Objective

We aimed to investigate mild AEs of Sputnik V based on a participatory trial conducted on Telegram in the Russian language. We compared AEs extracted from Telegram with other limited databases on Sputnik V and other COVID-19 vaccines. We explored symptom co-occurrence patterns and determined how counts of administered doses, age, gender, and sequence of shots could confound the reporting of AEs.

Methods

We collected a unique dataset consisting of 11,515 self-reported Sputnik V vaccine AEs posted on the Telegram group, and we utilized natural language processing methods to extract AEs. Specifically, we performed multilabel classifications using the deep neural language model Bidirectional Encoder Representations from Transformers (BERT) “DeepPavlov,” which was pretrained on a Russian language corpus and applied to the Telegram messages. The resulting area under the curve score was 0.991. We chose symptom classes that represented the following AEs: fever, pain, chills, fatigue, nausea/vomiting, headache, insomnia, lymph node enlargement, erythema, pruritus, swelling, and diarrhea.

Results

Telegram users complained mostly about pain (5461/11,515, 47.43%), fever (5363/11,515, 46.57%), fatigue (3862/11,515, 33.54%), and headache (2855/11,515, 24.79%). Women reported more AEs than men (1.2-fold, P<.001). In addition, there were more AEs from the first dose than from the second dose (1.1-fold, P<.001), and the number of AEs decreased with age (β=.05 per year, P<.001). The results also showed that Sputnik V AEs were more similar to other vector vaccines (132 units) than with messenger RNA vaccines (241 units) according to the average Euclidean distance between the vectors of AE frequencies. Elderly Telegram users reported significantly more (5.6-fold on average) systemic AEs than their peers, according to the results of the phase 3 clinical trials published in The Lancet. However, the AEs reported in Telegram posts were consistent (Pearson correlation r=0.94, P=.02) with those reported in the Argentinian postmarketing AE registry.

Conclusions

After the Sputnik V vaccination, Russian Telegram users reported mostly pain, fever, and fatigue. The Sputnik V AE profile was comparable with other vector COVID-19 vaccines. Discussion on social media could provide meaningful information about the AE profile of novel vaccines.

Parental vaccine hesitancy: scope, causes, and potential responses

PURPOSE OF REVIEW

We reviewed the literature about parental vaccine hesitancy, focusing on publications from October 2019 to April 2021 to describe patterns and causes of hesitancy and interventions to address hesitancy.

RECENT FINDINGS

Recent studies expand understanding of the prevalence of vaccine hesitancy globally and highlight associated individual and contextual factors. Common concerns underlying hesitancy include uncertainty about the need for vaccination and questions about vaccine safety and efficacy. Sociodemographic factors associated with parental vaccine hesitancy vary across locations and contexts. Studies about psychology of hesitancy and how parents respond to interventions highlight the role of cognitive biases, personal values, and vaccination as a social contract or norm. Evidence-based strategies to address vaccine hesitancy include presumptive or announcement approaches to vaccine recommendations, motivational interviewing, and use of immunization delivery strategies like standing orders and reminder/recall programs. A smaller number of studies support use of social media and digital applications to improve vaccination intent. Strengthening school vaccine mandates can improve vaccination rates, but policy decisions must consider local context.

SUMMARY

Vaccine hesitancy remains a challenge for child health. Future work must include more interventional studies to address hesitancy and regular global surveillance of parental vaccine hesitancy and vaccine content on social media.

Young adults' preferences for influenza vaccination campaign messages: Implications for COVID-19 vaccine intervention design and development

Background

Health campaign interventions, particularly those tailored to the target audience's needs and preferences, can cost-effectively change people's attitudes and behaviors towards better health decision-making. However, there is limited research on how to best tailor seasonal influenza vaccination campaigns for young adults. Vaccination is vital in protecting young adults and their social circles (vulnerable populations like older adults) from the influenza virus and critical in shaping these emerging adults' vaccination habits in the long run. However, amid the prevalence of easily-accessible, attention-grabbing, and often malicious false and misinformation (e.g., COVID-19 vaccine conspiracy theories), it may be more challenging to develop vaccination messages that resonate with young adults well enough to attract their attention. Therefore, to bridge the research gap, this study examines young adults' preferences for seasonal influenza vaccination campaigns to inform effective intervention design and development.

Methods

Qualitative survey questions were developed to gauge young adults' preferences for seasonal influenza vaccination campaigns. A total of 545 young adults (73.9% female, Mage ​= ​19.89, SD ​= ​1.44) from a large University offered complete answers to a cross-sectional online survey. Braun and Clarke's thematic analysis procedures were adopted to guide the data analysis process.

Results

Thematic analysis revealed that young adults prefer seasonal influenza vaccination campaigns that rely on (1) quality and balanced information from (2) credible information sources, positioned in the (3) relevant health contexts, (4) emphasize actionable messages, and incorporate (5) persuasive campaign design. Interestingly, while many participants underscored the importance of fear-appeal messages in persuading them to take health actions, some young adults also suggested avoiding fear campaigns due to discomfort.

Conclusions

Insights of the study can inform seasonal influenza vaccination design and development, and have the potential to shed light on vaccination messaging in other vaccine contexts, such as COVID-19 vaccines. Results also underscore the need for health experts and government officials to adopt a more nuanced approach when selecting persuasive campaign appeals. While some young adults may resonate well with fear appeals, others may not. Future research could examine the underlying mechanisms that drive young adults' preference for vaccination campaign intervention to enrich the literature further.

Public attitudes toward COVID-19 vaccines on English-language Twitter: A sentiment analysis

Objective

To identify themes and temporal trends in the sentiment of COVID-19 vaccine-related tweets and to explore variations in sentiment at world national and United States state levels.

Methods

We collected English-language tweets related to COVID-19 vaccines posted between November 1, 2020, and January 31, 2021. We applied the Valence Aware Dictionary and sEntiment Reasoner tool to calculate the compound score to determine whether the sentiment mentioned in each tweet was positive (compound ≥ 0.05), neutral (-0.05 < compound < 0.05), or negative (compound ≤ -0.05). We applied the latent Dirichlet allocation analysis to extract main topics for tweets with positive and negative sentiment. Then we performed a temporal analysis to identify time trends and a geographic analysis to explore sentiment differences in tweets posted in different locations.

Results

Out of a total of 2,678,372 COVID-19 vaccine-related tweets, tweets with positive, neutral, and negative sentiments were 42.8%, 26.9%, and 30.3%, respectively. We identified five themes for positive sentiment tweets (trial results, administration, life, information, and efficacy) and five themes for negative sentiment tweets (trial results, conspiracy, trust, effectiveness, and administration). On November 9, 2020, the sentiment score increased significantly (score = 0.234, p = 0.001), then slowly decreased to a neutral sentiment in late December and was maintained until the end of January. At the country level, tweets posted in Brazil had the lowest sentiment score of −0.002, while tweets posted in the United Arab Emirates had the highest sentiment score of 0.162. The overall average sentiment score for the United States was 0.089, with Washington, DC having the highest sentiment score of 0.144 and Wyoming having the lowest sentiment score of 0.036.

Conclusions

Public sentiment on COVID-19 vaccines varied significantly over time and geography. Sentiment analysis can provide timely insights into public sentiment toward the COVID-19 vaccine and guide public health policymakers in designing locally tailored vaccine education programs.

Prediction of vaccine hesitancy based on social media traffic among Israeli parents using machine learning strategies

Introduction

Vaccines have contributed to substantial reductions of morbidity and mortality from vaccine-preventable diseases, mainly in children. However, vaccine hesitancy was listed by the World Health Organization (WHO) in 2019 as one of the top ten threats to world health.

Aim

To employ machine-learning strategies to assess how on-line content regarding vaccination affects vaccine hesitancy.

Methods

We collected social media posts and responses from vaccination discussion groups and forums on leading social platforms, including Facebook and Tapuz (A user content website that contains blogs and forums). We investigated 65,603 records of children aged 0–6 years who are insured in Maccabi’s Health Maintenance Organization (HMO). We applied three machine learning algorithms (Logistic regression, Random forest and Neural networks) to predict vaccination among Israeli children, based on demographic and social media traffic.

Results

Higher hesitancy was associated with more social media traffic, for most of the vaccinations. The addition of the social media traffic features improved the performances of most of the models.

However, for Rota virus, Hepatitis A and hepatitis B, the performances of all algorithms (with and without the social media features) were close to random (accuracy up to 0.63 and F1 up to 0.65). We found a negative association between on-line discussions and vaccination.

Conclusions

There is an association between social media traffic and vaccine hesitancy. Policy makers are encouraged to perceive social media as a main channel of communication during health crises. Health officials and experts are encouraged to take part in social media discussions, and be equipped to readily provide the information, support and advice that the public is looking for, in order to optimize vaccination actions and to improve public health

Supplementary Information

The online version contains supplementary material available at 10.1186/s13584-021-00486-6.

A Multi-platform Approach to Monitoring Negative Dominance for COVID-19 Vaccine-Related Information Online

OBJECTIVE

The aim of this study was to test the appearance of negative dominance in COVID-19 vaccine-related information and activity online. We hypothesized that if negative dominance appeared, it would be a reflection of peaks in adverse events related to the vaccine, that negative content would attract more engagement on social media than other vaccine-related posts, and posts referencing adverse events related to COVID-19 vaccination would have a higher average toxicity score.

METHODS

We collected data using Google Trends for search behavior, CrowdTangle for social media data, and Media Cloud for media stories, and compared them against the dates of key adverse events related to COVID-19. We used Communalytic to analyze the toxicity of social media posts by platform and topic.

RESULTS

While our first hypothesis was partially supported, with peaks in search behavior for image and YouTube videos driven by adverse events, we did not find negative dominance in other types of searches or patterns of attention by news media or on social media.

CONCLUSION

We did not find evidence in our data to prove the negative dominance of adverse events related to COVID-19 vaccination on social media. Future studies should corroborate these findings and, if consistent, focus on explaining why this may be the case.