Date of Award
Master of Science (MS)
Healthcare technology is growing in its capabilities and capacity to impact people’s daily lives. One area of interest for growth is the use of chatbots and other telehealth applications that allow people to receive ubiquitous health information. The benefit of these systems is the ability to give access to pertinent, personalized healthcare information and services that could otherwise be inaccessible for some populations. With personalized information, patients may gain the information needed to make efficacious healthcare decisions which ideally will result in quicker recovery times and lower overall healthcare system costs. Chatbots have already been studied in the healthcare domain as resources for smoking cessation, diet recommendation, and other assistive applications. Yet, few studies have examined the specific design characteristics of healthcare chatbots. My research objective was to analyze two characteristics, language and persona, and their effect on outcomes such as effectiveness, usability, and trust in a chatbot. A between-subject study was performed where participants interacted with a chatbot. Each of chatbot conditions had a language of either technical or non-technical, and persona of Doctor, Nurse, or Nursing Student Sarah. Language was found to have a significant effect on effectiveness, but not trust or usability. In particular, participants who experienced technical language improved significantly greater than those who experienced non-technical language. Persona was found to not be significant for any of the outcomes. Overall, this study demonstrated a need to further study and understand how chatbot design characteristics impact users and how they comprehend the information given to them, particularly from a healthcare perspective.
Linder, Courtney, "The Effects of a Healthcare Chatbots' Language and Persona on User Trust, Satisfaction, and Chatbot Effectiveness" (2020). All Theses. 3299.