What Do We Know About the Use of Chatbots for Public Health?
Methods: We carried out a literature review on this topic across 5 databases: Pubmed, EMBASE, PsychINFO, SCOPUS, and IEEE Xplore. Identified papers were classified according to their underlying technology, application area, and study design.
Results: A total of 15 relevant papers were identified: eight of these papers were developmental studies that tested the feasibility or usability of a chatbot, and seven were interventional studies. All the interventional studies reported positive health- related outcomes associated with the chatbot use.
Discussion: The first studies testing chatbots for public health seem very promising; however, there are various aspects that should be improved, including the chatbots’ designs, studies’ methods, and analysis and reporting of results. More high-quality studies and improved reporting of chatbots’ use are needed.