Adaptive Conversational Agents: Exploring the Effect of Individualized Design on User Experience

Conversational agents (CA) offer a range of benefits to firms and users, yet user experiences are often unsatisfying. An explanation might be that individual differences of users are only insufficiently addressed in today’s CA design. Drawing on communication accommodation theory, we develop a research model and study design to investigate how adapting CA design to users’ individual characteristics influences the user experience. In particular, we develop text-based CAs (i.e., chatbots) that are adapted to users’ rational/intuitive cognitive style or need for interaction, and compare the user experience to non-adapted CAs. Initial results from our pilot study (n=37) confirm that individualized CA design can enhance the user experience. We expect to contribute to the growing research field of adaptive CA design. Moreover, our results will provide guidance for developers on how to facilitate a pleasing user experience by adapting the CA design to users.