Democratizing the development of chatbots to improve public health: A feasibility study of COVID-19 misinformation.

BACKGROUND: Chatbots are becoming more commonplace in our daily lives, especially in marketing, customer support, and even healthcare. Chatbots enable users to have humanlike conversations on various topics and can vary widely in complexity and functionality. Recent advancements in chatbot development technology have allowed low and middle resource environments to move into the chatbot space. An area of research priority in chatbots is democratizing chatbots to all. Democratizing chatbots means removing barriers to entry, such as financial, technical, or specialized human resources, to help make chatbots a possibility for the wider global population, the goal of which is to improve access to information, help to reduce the digital divide between nations, and to improve areas of public good. One application for chatbots for public good is in the area of health communication. Chatbots in this space may help create the potential for improved health outcomes, potentially alleviating some of the burdens on healthcare providers and healthcare systems to be the sole voices of outreach to public health. OBJECTIVE: This study explores the feasibility of developing a chatbot utilizing approaches that are accessible in low and middle resource settings. This includes using technology that is low cost, can be developed by non-programmers, can be deployed over social media platforms to reach the broadest possible audience without the need for a specialized technical team, using freely available and accurate knowledge bases, and developed using evidence-based practices to create a conversational model that integrates the potential for a change in health behaviors. METHODS: This study is presented in two parts. First, our Methods details the design and development of a chatbot, including the resources used and development considerations for the conversational model. The Results present a case study of thirty-three participants who engaged in a pilot with our chatbot. The paper explores the following research questions: 1) Is it feasible to develop and implement a chatbot addressing a public health issue with only minimal resources?, 2) What is the participants' experience with using the chatbot?, 3) What kinds of measures of engagement are observed from using the chatbot? RESULTS: Our early findings from this initial pilot suggest that developing a functioning and low cost chatbot is feasible even in low resource environments. A convenience sample of 33 participants was selected. A high level of engagement with the bot was demonstrated by the number of participants who stayed with the conversation to its natural end, requested to see the free online resource, selected to view all information about a given concern, and by the percentage of participants who returned to have a dialogue about a second concern. Over half of the participants (n=17, 52%) continued the conversation until the end, and around 36% (n=12) went for a second chat. CONCLUSIONS: This study has served to explore the feasibility and expose the design and development considerations for VWise, a chatbot created to enable a greater diversity of environments to enter the chatbot space by using readily available human and technical resources. Our study found promise that low resource environments can enter the health communication chatbot space. However, despite these early indicators, many limitations existed in this study and further work is needed with a larger sample size and greater diversity of participants. This study represents a very early work of a chatbot in its virtual infancy. We hope this study will help provide those who feel chatbot access may be out of reach with a useful guide to entering this space, enabling more democratized access to chatbots for all.

A Web-Based Public Health Intervention for Addressing Vaccine Misinformation: Analysis of Learner Engagement and Shift in Hesitancy to Vaccinate.

Web-based public health interventions can be a useful tool for disseminating evidence-based information to the public. However, completion rates are traditionally low, and misinformation often travels at a faster pace than evidence-based sources. This study describes the design of a web-based public health intervention to address COVID-19 vaccine hesitancy. A quasi-experimental approach was used in which a validated instrument, the Adult Vaccine Hesitancy Survey, was given to learners both pre and post intervention to observe any change in attitude towards vaccination. Our pilot observed a small positive shift in vaccine hesitancy and experienced higher than average completion rates. By integrating motivational learning design into public health interventions we increase the likelihood that learners finish the entire intervention, creating greater chance for positive behavior change.

Contextual Conversational Agent to Address Vaccine Hesitancy: Protocol for a Design-Based Research Study.

BACKGROUND: Since the beginning of the COVID-19 pandemic, people have been exposed to misinformation, leading to many myths about SARS-CoV-2 and the vaccines against it. As this situation does not seem to end soon, many authorities and health organizations, including the World Health Organization (WHO), are utilizing conversational agents (CAs) in their fight against it. Although the impact and usage of these novel digital strategies are noticeable, the design of the CAs remains key to their success. OBJECTIVE: This study describes the use of design-based research (DBR) for contextual CA design to address vaccine hesitancy. In addition, this protocol will examine the impact of DBR on CA design to understand how this iterative process can enhance accuracy and performance. METHODS: A DBR methodology will be used for this study. Each phase of analysis, design, and evaluation of each design cycle inform the next one via its outcomes. An anticipated generic strategy will be formed after completing the first iteration. Using multiple research studies, frameworks and theoretical approaches are tested and evaluated through the different design cycles. User perception of the CA will be analyzed or collected by implementing a usability assessment during every evaluation phase using the System Usability Scale. The PARADISE (PARAdigm for Dialogue System Evaluation) method will be adopted to calculate the performance of this text-based CA. RESULTS: Two phases of the first design cycle (design and evaluation) were completed at the time of this writing (April 2022). The research team is currently reviewing the natural-language understanding model as part of the conversation-driven development (CDD) process in preparation for the first pilot intervention, which will conclude the CA's first design cycle. In addition, conversational data will be analyzed quantitatively and qualitatively as part of the reflection and revision process to inform the subsequent design cycles. This project plans for three rounds of design cycles, resulting in various studies spreading outcomes and conclusions. The results of the first study describing the entire first design cycle are expected to be submitted for publication before the end of 2022. CONCLUSIONS: CAs constitute an innovative way of delivering health communication information. However, they are primarily used to contribute to behavioral change or educate people about health issues. Therefore, health chatbots' impact should be carefully designed to meet outcomes. DBR can help shape a holistic understanding of the process of CA conception. This protocol describes the design of VWise, a contextual CA that aims to address vaccine hesitancy using the DBR methodology. The results of this study will help identify the strengths and flaws of DBR's application to such innovative projects.

A Web-Based Public Health Intervention for Addressing Vaccine Misinformation: Protocol for Analyzing Learner Engagement and Impacts on the Hesitancy to Vaccinate.

BACKGROUND: A barrier to successful COVID-19 vaccine campaigns is the ongoing misinformation pandemic, or infodemic, which is contributing to vaccine hesitancy. Web-based population health interventions have been shown to impact health behaviors positively. For web-based interventions to be successful, they must use effective learning design strategies that seek to address known issues with learner engagement and retention. To know if an intervention successfully addresses vaccine hesitancy, there must be some embedded measure for comparing learners preintervention and postintervention. OBJECTIVE: This protocol aims to describe a study on the effectiveness of a web-based population health intervention that is designed to address vaccine misinformation and hesitancy. The study will examine learner analytics to understand what aspects of the learning design for the intervention were effective and implement a validated instrument-the Adult Vaccine Hesitancy Scale-to measure if any changes in vaccine hesitancy were observed preintervention and postintervention. METHODS: We developed a fully web-based population health intervention to help learners identify misinformation concerning COVID-19 and share the science behind vaccinations. Intervention development involves using a design-based research approach to output more effective interventions in which data can be analyzed to improve future health interventions. The study will use a quasi-experimental design in which a pre-post survey will be provided and compared statistically. Learning analytics will also be generated based on the engagement and retention data collected through the intervention to understand what aspects of our learning design are effective. RESULTS: The web-based intervention was released to the public in September 2021, and data collection is ongoing. No external marketing or advertising has been done to market the course, making our current population of 486 participants our pilot study population. An analysis of this initial population will enable the revision of the intervention, which will then be marketed to a broader audience. Study outcomes are expected to be published by August 2022. We anticipate the release of the revised intervention by May 2022. CONCLUSIONS: Disseminating accurate information to the public during pandemic situations is vital to contributing to positive health outcomes, such as those among people getting vaccinated. Web-based interventions are valuable, as they can reach people anytime and anywhere. However, web-based interventions must use sound learning design to help incentivize engagement and motivate learners to learn and must provide a means of evaluating the intervention to determine its impact. Our study will examine both the learning design and the effectiveness of the intervention by using the analytics collected within the intervention and a statistical analysis of a validated instrument to determine if learners had a change in vaccine hesitancy as a result of what they learned. INTERNATIONAL REGISTERED REPORT IDENTIFIER (IRRID): DERR1-10.2196/38034.

Conversational Agent to Address COVID-19 Infodemic: A Design-Based Research Approach.

Since the beginning of the year 2020, we have been suffering from the COVID-19 pandemic and are daily exposed to misinformation, leading to myths around vaccination and COVID-19. This study focuses on creating and distributing a Conversational Agent (CA), named VWise, for a health intervention using Design-Based Research (DBR), to help profile, guide, and inform the public about COVID-19 and COVID-19 vaccination in the EMRO (Eastern Mediterranean Region of Operations) region.

Adult Vaccine Hesitancy Scale in Arabic and French: Protocol for Translation and Validation in the World Health Organization Eastern Mediterranean Region.

BACKGROUND: The world as we know it changed during the COVID-19 pandemic. Hope has emerged with the development of new vaccines against the disease. However, many factors hinder vaccine uptake and lead to vaccine hesitancy. Understanding the factors affecting vaccine hesitancy and how to assess its prevalence have become imperative amid the COVID-19 pandemic. The vaccine hesitancy scale (VHS), developed by the World Health Organization (WHO) Strategic Advisory Group of Experts on Immunization, has been modified to the adult VHS (aVHS) and validated in English and Chinese. To our knowledge, no available aVHS has been designed or validated in Arabic or French. OBJECTIVE: The aim of this research is to translate the aVHS from its original English language to Arabic and French and validate the translations in the WHO Eastern Mediterranean region. METHODS: The study will follow a cross-sectional design divided into 5 phases. In phase 1, the original aVHS will be forward-translated to Arabic and French, followed by backward translation to English. An expert committee will review and rate all versions of the translations. Expert agreement will then be measured using the Cohen kappa coefficient (k). In phase 2, the translated aVHS will be pilot-tested with 2 samples of participants (n=100): a group that speaks both Arabic and English and another that speaks French and English. Participants' responses to the English version will also be collected. In phase 3, responses will then be compared. Descriptive statistics and paired t tests or one-way analyses of variance (ANOVA) and Pearson correlation coefficient will be used in the preliminary validation. In phase 4, prefinal versions (Arabic and French) will be tested with larger sample sizes of Arabic speakers (n=1000) and French speakers (n=1000). Sociodemographic information and vaccination status will be collected and used for further analysis. In phase 5, the scale's statistical reliability and internal consistency will be measured using Cronbach alpha. An exploratory factor analysis (EFA) and confirmatory factor analysis (CFA) will be used to examine the model fit resulting from the EFA. ANOVA and regression models will be constructed to control for confounders. All data will be electronically collected. RESULTS: As of January 2022, the scale had been translated to Arabic and French and was undergoing the process of back translation. All data collection tools have been prepared (ie, sociodemographics, vaccination status, and open-ended questions) and are ready to go into their electronic formats. We expect to reach the desired sample size in this phase by June 2022. CONCLUSIONS: This study will provide researchers with a validated tool to assess adult vaccine hesitancy within populations that speak Arabic and/or French and provide a road map to scale translation and ensure cross-cultural adaptation. INTERNATIONAL REGISTERED REPORT IDENTIFIER (IRRID): PRR1-10.2196/36928.

Elements That Underpin the Design, Development, and Evaluation of Social Media Health Interventions: Protocol for a Scoping Review.

BACKGROUND: Social media use has grown tremendously over the years. Given the volume and diversity of people on social media and the amount of information being exchanged, it is perhaps unsurprising that social media is being used as an avenue to disseminate and deliver health interventions. There exists an opportunity for social media health interventions to make a positive impact on health. However, there is a need to understand more about the ways in which these interventions are designed, developed, and evaluated. This scoping protocol will review the current state of this field by charting the elements that drive the design, development, and evaluation of these interventions. This includes charting models, frameworks, and rationales for the interventions, as well as the platforms being used, and the health behaviors being targeted. This intention of this scoping review is to help inform those who wish to develop effective social media health interventions. OBJECTIVE: The objective of this review is to map the elements that drive the design, development, and evaluation of social media health interventions. We define "social media health intervention" as interventions that make use of social media platforms to disseminate or deliver health-related information and educational initiatives to the public. We will seek to chart the elements that drive the design, development, and delivery of such interventions, including their platforms and targeted health behaviors. METHODS: The methodological framework for this review is guided by Arksey and O'Malley and enhancements by later studies. We will search relevant literature from 9 databases: (1) PubMed, (2) PsycINFO, (3) EMBASE, (4) Web of Science, (5) Scopus, (6) CINAHL, (7) ERIC, (8) MEDLINE, and (9) Google Scholar. The literature will be screened by at least two reviewers in 2 stages: (1) title/abstract screening against the eligibility criteria; and (2) eligible articles will then undergo a full-text screening. Data will be charted using the data charting tool developed by the authors. RESULTS: The results of this study will be presented in a final scoping review paper, divided into 2 sections. The first section will describe the search strategy and study selection process and will contain the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) flowchart. The second section will provide key details pertaining to the review objective and question. CONCLUSIONS: This review will help guide scholars looking to build social media health interventions toward evidence-based practices in design and evaluation. INTERNATIONAL REGISTERED REPORT IDENTIFIER (IRRID): PRR1-10.2196/31911.