Probing context-sensitive expectations through user-driven personality configuration in conversational AI

Abstract

Abstract Conversational agents are increasingly expected to adapt across contexts and evolve their personalities through interactions, yet most remain static once configured. We present an exploratory study of how user expectations form and evolve when agent personality is made dynamically adjustable. To investigate this, we designed a prototype conversational interface that enabled users to adjust an agent’s personality along eight research-grounded dimensions across three task contexts: problem-focused guidance, affective coping, and reflective evaluation. We conducted an online mixed-methods study with 60 participants, employing latent profile analysis to characterise personality classes and trajectory analysis to trace evolving patterns of personality adjustment. These approaches revealed distinct personality profiles at initial and final configuration stages, and adjustment trajectories, shaped by context-sensitivity. We further identified design factors to reflect on when developing user-driven conversational AI. Our findings highlight the importance of designing conversational agents that adapt alongside their users, advancing more responsive and human-centred AI.