Piloting a COVID-19 vaccine chatbot with young adults and health workers in the U.S. to validate usability, credibility, and intention to use.

BACKGROUND: The COVID-19 pandemic raised novel challenges in communicating reliable, continually changing health information to a broad and sometimes skeptical public, particularly around COVID-19 vaccines, which despite being comprehensively studied were the subject of viral misinformation. Chatbots are a promising technology to reach and engage populations during the pandemic. To inform and communicate effectively with users, chatbots must be highly usable and credible. OBJECTIVE: We sought to understand how young adults and health workers in the U.S. assessed the usability and credibility of a web-based chatbot called Vira, created by the Johns Hopkins Bloomberg School of Public Health and IBM Research using natural language processing technology. Using a mixed-method approach, we sought to rapidly improve Vira's user experience to support vaccine decision-making during the peak of the COVID-19 pandemic. METHODS: We recruited racially and ethnically diverse young people and health workers, with both groups from urban areas of the U.S. We used the validated Chatbot Usability Questionnaire (CUQ) to understand the tool's navigation, precision, and persona. We also conducted 11 interviews with health workers and young people to understand the user experience, whether they perceived the chatbot as confidential and trustworthy, and how they would use the chatbot. We coded and categorized emerging themes to understand the determining factors for participants' assessment of chatbot usability and credibility. RESULTS: Fifty-eight participants completed an online usability questionnaire and 11 completed in-depth interviews. Most questionnaire respondents (86-88%) said the chatbot was "easy to navigate" and "very easy to use," and many (78%) said responses were relevant. The mean CUQ score was 70.2 ± 12.1 and scores ranged from 40.6 to 95.3. Interview participants felt the chatbot achieved high usability due to its strong functionality, performance, and perceived confidentiality, and that the chatbot could attain high credibility with a redesign of its cartoonish visual persona. Young people said they would use the chatbot to discuss vaccination with hesitant friends or family members, while health workers used or anticipated using the chatbot to support community outreach, save time, and stay up to date. CONCLUSIONS: This formative study conducted during the pandemic's peak provided user feedback for an iterative redesign of Vira. Taking a mixed-method approach provided multidimensional feedback, identifying how the chatbot worked well-being easy to use, answering questions appropriately, and using credible branding-while offering tangible steps to improve the product's visual design. Future studies should evaluate how chatbots support personal health decision-making, particularly in the context of a public health emergency, and whether such outreach tools can reduce staff burnout. Randomized studies should also measure how chatbots countering health misinformation affect user knowledge, attitudes, and behavior.

Digital Strategies to Improve Food Assistance in Disasters: A Scoping Review.

OBJECTIVE: Modern digital strategies, including Internet of Things, machine learning, and mobile applications, have revolutionized situational awareness during disaster management. Despite their importance, no review of digital strategies to support emergency food security efforts has been conducted. This scoping review fills that gap. METHODS: Keywords were defined within the concepts of food assistance, digital technology, and disasters. After the database searches, PRISMA guidelines were followed to perform a partnered, 2-round scoping literature review. RESULTS: The search identified 3201 articles, and 26 articles met criteria and were included in the analysis. The data types used to describe the tools were text/opinion (42.3%), qualitative (23.1%), system architecture (19.2%), quantitative and qualitative (11.5 %), and quantitative (3.8%). The tools' main functions were Resource Allocation (41.7%), Data Collection and Management (33%), Interagency Communications (15.4 %), Beneficiary Communications (11.5%), and Fundraising (7.7%). The platforms used to achieve these goals were Mobile Application (36%), Internet of Things (20%), Website (20%), and Mobile Survey (8%); 92% covered the disaster response phase. CONCLUSIONS: Digital tools for planning, situational awareness, client choice, and recovery are needed to support emergency food assistance, but there is a lack of these tools and research on their effectiveness across all disaster phases.

Impact of the COVID-19 Pandemic on Food Accessibility Procurement for Baltimore City Corner Store Owners

Objectives Corner stores are small independently run retail outlets that serve their immediate neighborhoods. Since nutritious foods have high supply-side purchasing and transportation costs, these stores more readily stock energy-dense processed foods and sugar-sweetened beverages. To improve the cost-effective distribution of healthy foods in an under-resourced urban food system, we are developing the Baltimore Urban food Distribution (BUD) mobile application (app), which aims to improve the ability for corner stores to stock healthier items via collective purchasing and shared delivery from local suppliers. No studies have been conducted on how COVID-19 has impacted food procurement by corner stores. This study aims to (1) list corner store sourcing and procurement strategies pre- and post-COVID-19;(2) quantify corner store sales and traffic pre- and post-COVID-19;and (3) identify perceived barriers to the supply chain because of COVID-19. Methods In-depth interviews (n = 13) and unstructured interviews (n = 28) with Baltimore, MD corner store owners have been ongoing since December 2021, where 38 stores are anticipated to be recruited by spring of 2022. Interviews took place at the corner store lasting 60 minutes, and included one survey, the Store Impact Questionnaire (SIQ) and Adult Impact Questionnaire (AIQ) and additional open-ended questions. Results Corner store owner food procurement strategies have changed, and they have experienced decreased traffic and sales since the onset of COVID-19. This includes having to minimize what is offered in the store, having less availability of healthy items, and using fewer vendors. We anticipate this study will further demonstrate that food procurement practices were destabilized because of COVID-19. Conclusions Understanding the impact of COVID-19 is crucial in improving the distribution tactics implemented by the BUD to ensure continuous availability of affordable, healthy foods and beverages. The success of the BUD app is dependent on meeting the needs of corner store owners and adapting to the changing food environment. Funding Sources NHLBI, NIH, award number R34HL145368.

The Baltimore Urban Food Distribution (BUD) App: Study Protocol to Assess the Feasibility of a Food Systems Intervention.

Low-income urban communities in the United States commonly lack ready access to healthy foods. This is due in part to a food distribution system that favors the provision of high-fat, high-sugar, high-sodium processed foods to small retail food stores, and impedes their healthier alternatives, such as fresh produce. The Baltimore Urban food Distribution (BUD) study is a multilevel, multicomponent systems intervention that aims to improve healthy food access in low-income neighborhoods of Baltimore, Maryland. The primary intervention is the BUD application (app), which uses the power of collective purchasing and delivery to affordably move foods from local producers and wholesalers to the city's many corner stores. We will implement the BUD app in a sample of 38 corner stores, randomized to intervention and comparison. Extensive evaluation will be conducted at each level of the intervention to assess overall feasibility and effectiveness via mixed methods, including app usage data, and process and impact measures on suppliers, corner stores, and consumers. BUD represents one of the first attempts to implement an intervention that engages multiple levels of a local food system. We anticipate that the app will provide a financially viable alternative for Baltimore corner stores to increase their stocking and sales of healthier foods, subsequently increasing healthy food access and improving diet-related health outcomes for under-resourced consumers. The design of the intervention and the evaluation plan of the BUD project are documented here, including future steps for scale-up. Trial registration #: NCT05010018.

Enhancing Artificial Intelligence for Twitter-based Public Discourse on Food Security During the COVID-19 Pandemic.

OBJECTIVE: Food security during public health emergencies relies on situational awareness of needs and resources. Artificial intelligence (AI) has revolutionized situational awareness during crises, allowing the allocation of resources to needs through machine learning algorithms. Limited research exists monitoring Twitter for changes in the food security-related public discourse during the COVID-19 pandemic. We aim to address that gap with AI by classifying food security topics on Twitter and showing topic frequency per day. METHODS: Tweets were scraped from Twitter from January 2020 through December 2021 using food security keywords. Latent Dirichlet Allocation (LDA) topic modeling was performed, followed by time-series analyses on topic frequency per day. RESULTS: 237,107 tweets were scraped and classified into topics, including food needs and resources, emergency preparedness and response, and mental/physical health. After the WHO's pandemic declaration, there were relative increases in topic density per day regarding food pantries, food banks, economic and food security crises, essential services, and emergency preparedness advice. Threats to food security in Tigray emerged in 2021. CONCLUSIONS: AI is a powerful yet underused tool to monitor food insecurity on social media. Machine learning tools to improve emergency response should be prioritized, along with measurement of impact. Further food insecurity word patterns testing, as generated by this research, with supervised machine learning models can accelerate the uptake of these tools by policymakers and aid organizations.

Chatbot-Delivered COVID-19 Vaccine Communication Message Preferences of Young Adults and Public Health Workers in Urban American Communities: Qualitative Study.

BACKGROUND: Automated conversational agents, or chatbots, have a role in reinforcing evidence-based guidance delivered through other media and offer an accessible, individually tailored channel for public engagement. In early-to-mid 2021, young adults and minority populations disproportionately affected by COVID-19 in the United States were more likely to be hesitant toward COVID-19 vaccines, citing concerns regarding vaccine safety and effectiveness. Successful chatbot communication requires purposive understanding of user needs. OBJECTIVE: We aimed to review the acceptability of messages to be delivered by a chatbot named VIRA from Johns Hopkins University. The study investigated which message styles were preferred by young, urban-dwelling Americans as well as public health workers, since we anticipated that the chatbot would be used by the latter as a job aid. METHODS: We conducted 4 web-based focus groups with 20 racially and ethnically diverse young adults aged 18-28 years and public health workers aged 25-61 years living in or near eastern-US cities. We tested 6 message styles, asking participants to select a preferred response style for a chatbot answering common questions about COVID-19 vaccines. We transcribed, coded, and categorized emerging themes within the discussions of message content, style, and framing. RESULTS: Participants preferred messages that began with an empathetic reflection of a user concern and concluded with a straightforward, fact-supported response. Most participants disapproved of moralistic or reasoning-based appeals to get vaccinated, although public health workers felt that such strong statements appealing to communal responsibility were warranted. Responses tested with humor and testimonials did not appeal to the participants. CONCLUSIONS: To foster credibility, chatbots targeting young people with vaccine-related messaging should aim to build rapport with users by deploying empathic, reflective statements, followed by direct and comprehensive responses to user queries. Further studies are needed to inform the appropriate use of user-customized testimonials and humor in the context of chatbot communication.

Current Use and Demand for Digital Tools to Enhance Food Pantry Management: Findings from a Nationwide Survey

Background Food insecurity has skyrocketed during the COVID-19 pandemic, compounded by critical limitations and unparalleled needs at food pantries. Interconnectivity between food pantry staff and clients is vital to food security. Digital tools are widely used in public health;however, little is known about current use or desire for digital tools in food pantry settings. Objective To define types of digital tools currently used for pantry management and identify gaps and interest in specific digital tool features to enhance pantry management. Study Design, Setting, Participants A cross-sectional online survey of U.S. food pantries was disseminated from January-May 2022. Using the foodpantries.org database, every tenth food pantry in each state was recruited via email and asked to complete the survey via Google Forms. The response rate was 27.4% (n=283/1,032). Most respondents (64.5%) identified as food pantry directors. Measurable Outcome/Analysis Descriptive statistics were used to characterize pantry location, size (pounds of food distributed), number of staff and volunteers (SV), use of a client choice model, and to describe the current tools used by pantries for multiple aspects of management. Results A majority (54.8%) of respondents represented large food pantries. Pantry-specific digital applications were rarely used. Instead, respondents reported using word-of-mouth and email to recruit SV, phone calls and emails for SV scheduling, and in-person classes for SV trainings. Clients were most often contacted via phone or email. There was high demand for an app for SV scheduling (50.2%), providing a safe, remote version of client choice (42.4%), client registration (35.7%), client and SV communications (35.0%), and connecting with nearby emergency services (22.3%). Conclusions Food pantry directors desired an app to support SV management, SV and client communication, safe client choice, and connection to emergency services. Future app development to enhance food pantry management and optimize food distribution is greatly needed. Funding None.

Moving Food Assistance into the Digital Age: A Scoping Review.

One of the most basic needs globally, food assistance refers to the multitude of programs, both governmental and non-governmental, to improve food access and consumption by food-insecure individuals and families. Despite the importance of digital and mobile Health (mHealth) strategies in food insecurity contexts, little is known about their specific use in food assistance programs. Therefore, the purpose of this study was to address that gap by conducting a scoping review of the literature. Keywords were defined within the concepts of food assistance and digital technology. The search included relevant peer-reviewed and grey literature from 2011 to 2021. Excluded articles related to agriculture and non-digital strategies. PRISMA guidelines were followed to perform a partnered, two-round scoping literature review. The final synthesis included 39 studies of which most (84.6%) were from the last five years and United States-based (93.2%). The top three types of articles or studies included text and opinion, qualitative research, and website, application, or model development (17.9%). The top three types of digital tools were websites (56.4%), smartphone applications (20.5%), and chatbots (5.1%). Nineteen digital features were identified as desirable. Most tools included just one or two features. The most popular feature to include was online shopping (n = 14), followed by inventory management, and client tracking. Digital tools for individual food assistance represent an opportunity for equitable and stable access to programs that can enhance or replace in-person services. While this review identified 39 tools, all are in early development and/or implementation stages. Review findings highlight an overall lack of these tools, an absence of user-centered design in their development, and a critical need for research on their effectiveness globally. Further analysis and testing of current digital tool usage and interventions examining the health and food security impacts of such tools should be explored in future studies, including in the context of pandemics, where digital tools allow for help from a distance.