Applications of Social Media and Digital Technologies in COVID-19 Vaccination: Scoping Review

Vaccination, Public Health and Health Communication: A Network of Connections to Tackle Global Challenges

Vaccination constitutes one of the most significant milestones in the history of Public Health [...].

The Collaboverse: A Collaborative Data-Sharing and Speech Analysis Platform

PURPOSE

Collaboration in the field of speech-language pathology occurs across a variety of digital devices and can entail the usage of multiple software tools, systems, file formats, and even programming languages. Unfortunately, gaps between the laboratory, clinic, and classroom can emerge in part because of siloing of data and workflows, as well as the digital divide between users. The purpose of this tutorial is to present the Collaboverse, a web-based collaborative system that unifies these domains, and describe the application of this tool to common tasks in speech-language pathology. In addition, we demonstrate its utility in machine learning (ML) applications.

METHOD

This tutorial outlines key concepts in the digital divide, data management, distributed computing, and ML. It introduces the Collaboverse workspace for researchers, clinicians, and educators in speech-language pathology who wish to improve their collaborative network and leverage advanced computation abilities. It also details an ML approach to prosodic analysis.

CONCLUSIONS

The Collaboverse shows promise in narrowing the digital divide and is capable of generating clinically relevant data, specifically in the area of prosody, whose computational complexity has limited widespread analysis in research and clinic alike. In addition, it includes an augmentative and alternative communication app allowing visual, nontextual communication.

Prioritization of Vaccines for Introduction in the National Immunization Program in the Republic of Korea

This study presents a framework for determining the prioritization of vaccine introduction in the National Immunization Program (NIP) of the Republic of Korea, with a focus on case examples assessed in 2021 and 2023. We describe the predefined criteria for evaluating the prioritization of vaccines in the NIP and the established process in the Republic of Korea. These criteria included disease characteristics, vaccine characteristics, rationality and efficiency of resource allocation, and the acceptance of immunization. The process of prioritizing NIP introduction involved several sequential steps: a demand survey, evidence collection, preliminary evaluation, priority evaluation, and decision making. In 2021 and 2023, 14 and 25 committee members participated in evaluating the prioritization of vaccines in the NIP, respectively. Overall, 13 and 19 NIP vaccine candidates were included in the 2021 and 2023 evaluations, respectively. Through the Delphi survey and consensus processes, the priority order was determined: vaccination against Rotavirus infection was the top priority in 2021, while Influenza 4v (for chronic disease patients) took precedence in 2023. This study demonstrates an evidence-based decision-making process within the healthcare field. The outlined approach may provide valuable guidance for policymakers in other countries seeking to prioritize the inclusion of new vaccines in their NIP.

COVID-19 information seeking and individuals' protective behaviors: examining the role of information sources and information content

BACKGROUND

Seeking COVID-19 information promotes individuals to adopt preventive behaviors, including wearing a mask, social distancing, staying away from risky places, and washing hands. This study aims to investigate which information and sources individuals relied on in seeking COVID-19 information and further examine their roles in individuals' adoption of preventive behaviors.

METHODS

Through a statistical analysis of 1027 valid responses from citizens in different Chinese cities in 2022 to the self-designed items in an online survey, this study identified individuals' preferred information sources and content on COVID-19. Regarding the information sources and content, the study used multiple regression analysis to examine their associations with individuals' preventive behaviors, and further applied fuzzy-set qualitative comparative analysis (fsQCA) to explore their configurations that increase the likelihood of individuals adopting preventive behaviors.

RESULTS

Individuals preferred information about the newest prevention and control policies, precautions and treatment, and symptoms from the sources of workplace and community, social media, and social live streaming services. Additionally, individuals' preventive behaviors were positively related to the workplace and community (β = 0.202, p <.001), social live streaming services (β = 0.089, p <.01), government department websites (β = 0.079, p <.05), television (β = 0.073, p <.05), and online news media (β = 0.069, p <.05), but were negatively associated with newspapers (β=-0.087, p <.05). Regarding information content, precautions and treatments (β = 0.211, p <.001), the newest prevention and control policies (β = 0.173, p <.001), symptoms (β = 0.152, p <.001), and official rumor-dispelling information (β = 0.082, p <.05) had a positive relationship with individuals' preventive behaviors. In addition, fsQCA results presented eight configurations that promote individuals to adopt preventive behaviors. The total coverage and solution consistency values were 0.869 and 0.987, respectively. Furthermore, COVID-19 information content, the sources of social media and interpersonal sources, and official news media played an essential role in increasing the likelihood of individuals adopting preventive behaviors.

CONCLUSIONS

Our findings demonstrated that individuals seek various COVID-19 information from multiple sources. The direct and degree of association of information sources and content with individuals' preventive behaviors vary from source to source and from content to content. Information sources and content could combinatorially promote individuals to adopt preventive behaviors through several configurations.

A Comparison of ChatGPT and Fine-Tuned Open Pre-Trained Transformers (OPT) Against Widely Used Sentiment Analysis Tools: Sentiment Analysis of COVID-19 Survey Data

BACKGROUND

Health care providers and health-related researchers face significant challenges when applying sentiment analysis tools to health-related free-text survey data. Most state-of-the-art applications were developed in domains such as social media, and their performance in the health care context remains relatively unknown. Moreover, existing studies indicate that these tools often lack accuracy and produce inconsistent results.

OBJECTIVE

This study aims to address the lack of comparative analysis on sentiment analysis tools applied to health-related free-text survey data in the context of COVID-19. The objective was to automatically predict sentence sentiment for 2 independent COVID-19 survey data sets from the National Institutes of Health and Stanford University.

METHODS

Gold standard labels were created for a subset of each data set using a panel of human raters. We compared 8 state-of-the-art sentiment analysis tools on both data sets to evaluate variability and disagreement across tools. In addition, few-shot learning was explored by fine-tuning Open Pre-Trained Transformers (OPT; a large language model [LLM] with publicly available weights) using a small annotated subset and zero-shot learning using ChatGPT (an LLM without available weights).

RESULTS

The comparison of sentiment analysis tools revealed high variability and disagreement across the evaluated tools when applied to health-related survey data. OPT and ChatGPT demonstrated superior performance, outperforming all other sentiment analysis tools. Moreover, ChatGPT outperformed OPT, exhibited higher accuracy by 6% and higher F-measure by 4% to 7%.

CONCLUSIONS

This study demonstrates the effectiveness of LLMs, particularly the few-shot learning and zero-shot learning approaches, in the sentiment analysis of health-related survey data. These results have implications for saving human labor and improving efficiency in sentiment analysis tasks, contributing to advancements in the field of automated sentiment analysis.

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.

Sources of Information about COVID-19 Vaccines for Children and Its Associations with Parental Motivation to Have Their Children Vaccinated in Taiwan

Pediatric COVID-19 vaccines have been developed to reduce the risk of contracting COVID-19 and subsequent hospitalization in children. Few studies have examined whether different sources of information regarding pediatric COVID-19 vaccines and parents' trust in the information have different effects on parental motivation to have their child vaccinated. No study has examined parental demographic factors related to the sources of information and the trust of parents in these sources. Understanding the sources of information on pediatric COVID-19 vaccines, parents' trust in the information, and related factors can contribute to the development of strategies for promoting the knowledge and acceptance of pediatric vaccination among parents. This study examined the sources of information regarding pediatric COVID-19 vaccines used by parents, their level of trust in these information sources, the demographic factors that influence this trust, and the associations of such information sources with parental motivation to get their child vaccinated against COVID-19. In total, 550 parents (123 men and 427 women) completed a questionnaire that was used to collect information regarding the information sources and to measure the parents' trust in these information sources. Parental motivation to get their child vaccinated was measured using the Motors of COVID-19 Vaccination Acceptance Scale for Parents. Multivariate linear regression analysis was performed to examine two associations, namely the associations of the parents' sources of information and their trust in these sources with their motivation to have their child vaccinated and the associations of the parents' demographic factors with their sources of information and their trust in these sources. For the parents, traditional mass media and medical staff in healthcare settings were the most common sources of information regarding pediatric COVID-19 vaccines. The parents rated medical staff in healthcare settings as the most trustworthy source of information. Obtaining information from acquaintances through social media and obtaining information from medical staff in healthcare settings were significantly associated with parental motivation to get their child vaccinated against COVID-19. Trust in the information provided by medical staff in healthcare settings and coworkers was significantly associated with the motivation of parents to vaccinate their children against COVID-19. Compared with fathers, mothers were more likely to obtain information from medical staff in healthcare settings and from acquaintances through social media. Parents with a higher education level were more likely to obtain information from medical staff in healthcare settings. Compared with the fathers, the mothers were more trusting of information obtained from coworkers. Health professionals should consider the sources of information used by parents and related factors when establishing strategies to increase parental motivation to get their children vaccinated against COVID-19.