Conversational Agents in Health Education: A Scoping Review Protocol (Preprint)

Abstract

Conversational agents can reach people where they are at, existing online, on mobile phones, or even through hardware like Alexa and Siri, making information easier to access and providing an engaging method of interaction. It makes sense that chatbots would also start to emerge to improve public health through health education. While building a chatbot is getting easier, there is still required time and effort. There is also a lack of clarity and consistent terminology about what kinds of chatbots are out there, how they are developed, and the kind of resources needed to develop and sustain them. This lack of clarity makes a daunting task for those seeking to build health education initiatives. Our scoping review seeks to categorize conversational agents in healthcare education in alignment with current classifications and terminology emerging from the marketplace. We will define the terminology of levels of conversational agents, categorize current agents along with these levels and describe the uses, resources, and evaluations common to these levels.

This scoping review aims to identify literature that reports on the design and implementation of conversational agents to promote and educate the public on matters related to health.

This scoping review will be conducted by employing the Arksey and O’Malley framework. We will also be adhering to the enhancements and updates proposed by Levac et al. and Peters et al. The PRISMA extension for scoping reviews will guide the reporting of this scoping review. A systematic search for published and grey literature will be undertaken from the following databases (1) PubMed, (2) PsychINFO, (2) Embase, (4) Web of Science, (5) SCOPUS, (6) CINAHL, (7) ERIC, (8) MEDLINE, (9) Google Scholar. Data charting will be done using a structured format.

Initial searches of the databases retrieved 1,480 results. The results will be presented in the final scoping review in both a narrative and illustrative manner.

Reviewers have previously explored conversational agents in health. However, to the authors' knowledge, there has been no review conducted in the specific area of our interest –Health Education. Therefore, this review will provide a map of the literature in this area and clarify and define the heterogeneous terms found in the literature. This information will help healthcare professionals and administrators to understand what kinds of chatbots would be appropriate in their setting. And through our charted data could also help them understand what kind of resources or expertise is required for the different chatbots in use.