Understanding User Preferences in Developing a Mental Healthcare AI Chatbot: A Conjoint Analysis Approach

Abstract

The global population is experiencing a significant rise in cases of depressive disorders, which have been exacerbated by the COVID-19 pandemic. However, having limited resources and fear of social stigma have discouraged individuals from seeking professional psychological counseling or visiting hospitals. In response to this issue, psychiatrists have attempted the use of chatbots as a therapeutic aid. Therefore, in this study, users’ choice data about the mental healthcare AI chatbot are collected through conjoint analysis, and the collected data is analyzed using the mixed logit method to derive users’ preferences for the mental healthcare AI chatbot. Findings highlight a consistent preference among users for certain factors in both psychological counseling chatbots and traditional psychological counseling. At first, the findings indicate that users place the highest priority on pricing and the ability to connect with a professional counselor. Furthermore, users prefer chatbots that have a more human-like appearance and characteristics. By incorporating these preferences, chatbot developers can create a more user-centric mental healthcare AI chatbot.