From Fixed to Flexible: Shaping AI Personality in Context-Sensitive Interaction

TL;DR

This study explores how users expect and adapt to AI personalities that can be dynamically adjusted across different contexts, emphasizing the importance of flexible, user-responsive conversational agents.

Contribution

It introduces a prototype interface enabling real-time personality adjustments and analyzes user interaction patterns and perceptions in diverse task contexts.

Findings

Users form distinct personality profiles at different stages.

Context influences personality adjustment trajectories.

Participants valued autonomy and trusted more when agents adapted.

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: informational, emotional, and appraisal. We conducted an online mixed-methods study with 60 participants, employing latent profile analysis to characterize 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. Participants also valued the autonomy, perceived the agent as more anthropomorphic, and reported greater trust. Our findings highlight the importance of designing conversational agents that adapt alongside their users, advancing more responsive and human-centred AI.