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

TL;DR

This study investigates dynamic, user-driven shaping of AI personality across eight dimensions in three context-specific tasks (Informational, Emotional, Appraisal). Using a GPT-4.1–powered interface, 60 participants adjusted personality sliders in real time, with analyses including Latent Profile Analysis, trajectory clustering, and Trust in Automation comparisons. Findings show context-sensitive expectations, baseline traits (Engagement, Serviceability, Decency) driving consistency across contexts, and distinct adjustment trajectories (steady, adaptive, reactive) that enhance perceived relationality and trust. The work highlights design implications for flexible, human-centered AI that adapts to user needs while balancing anthropomorphism and ethical considerations. Overall, it provides actionable guidelines for building responsive conversational agents that maintain competence, transparency, and trust through co-constructed personality configurations.

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.

Figures (14)

• Figure 1: The main conversational interface. (A) Slider panel for configuring and fine-tuning the agent’s personality across eight dimensions. (B) Conversational area for task-based interaction with the agent. (C) Information panel providing step-by-step instructions and guidance for using the interface.
• Figure 2: Overview of the user study procedure, from consent and pre-task measures through task-based chatbot interactions, post-task surveys, and post-study questionnaire.
• Figure 3: Latent profile analysis (LPA) results in Informational condition. The left panel shows the initial configuration profiles, and the right panel shows the final configuration profiles. All LPA figures are provided in Appendix \ref{['sec:lpa_profiles']}.
• Figure 4: Sankey diagrams illustrating the transitions of latent personality profiles from initial to final configurations across the three experimental conditions: (\ref{['fig:lpa_info']}) Informational, (\ref{['fig:lpa_emo']}) Emotional, and (\ref{['fig:lpa_app']}) Appraisal. The width of each flow represents the proportion of participants shifting between profiles.
• Figure 5: Heat-map of net personality changes across the three conditions (Informational, Emotional, Appraisal).