JMIR Publications

ABSTRACT

Background:

Since the beginning of the COVID-19 pandemic, people have been exposed to misinformation which led to many myths around the virus and the vaccination against it. As this situation doesn't seem to end soon, many authorities and health organizations, including the World Health Organization, have already utilized conversational agents' technology in their fight against it. Although the impact and usage of these novel digital strategies are noticeable, the design of the conversational agents remains key to their success.

Objective:

This study explores the use of design-based research for contextual conversational agent design to address vaccine hesitancy. This protocol will examine the application of iterative design cycles that will result with the release of VWise, a conversational agent (CA) that address, profile, and advise on Covid-19 vaccination.

Methods:

As with every design-based research study, the idea of iterative and continuous development aligns perfectly with the aim of this project. 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. Quality improvement of the conversational agent will be carried out by the adoption of a usability assessment during every evaluation phase using the System Usability Scale. The PARADISE paradigm will be adapted to calculate the performance of this text-based chatbot.

Results:

Two phases of the first design cycle had been completed at the time of authoring this paper. The research team is currently reviewing the NLU model as part of the CDD process in preparation for the first pilot intervention, which will conclude the CA's first design cycle. Conversational data gathered through Rasa GUI will be analyzed quantitatively and qualitatively as part of the reflection and revision process to inform the subsequent design cycles. This project has three rounds of design cycles planned, which will result in various studies spreading outcomes and conclusions. The first study result describing the entire initial design cycle is expected to be published by June 2022.

Conclusions:

Conversational agents constitute an innovative way of delivering health communication information. They are primarily used to either contribute to behavioral change or educate about health issues. Therefore, health chatbots' impact should be carefully designed to meet outcomes. Design-Based Research (DBR) can help shape a holistic understanding of the process of conversational agent conception. This protocol will describe the design of VWise, a contextual conversational agent that aims to address vaccine hesitancy using the DBR methodology. The results of this study will help identify the strength and flaws of its application to such innovative projects.