ExplainabilityTrustworthinessTransparencycs.HC
Exploring Personality-Driven Personalization in XAI: Enhancing User Trust in Gameplay
Zhaoxin Li, Sophie Yang, Shijie Wang
August 8, 2024
arXiv.org
2 citations
Key Takeaways
-
Personality matters in AI explanations: The research demonstrates that how people prefer to understand AI decisions varies based on their personality traits (measured through the Big Five personality framework), suggesting a one-size-fits-all approach to AI transparency is insufficient for building user trust.
-
Personalized explanations increase user acceptance: When AI systems tailored their explanations to match individual personality profiles in a gaming context, users were "more receptive to personalized XAI recommendations," indicating that customization can meaningfully improve how people engage with AI systems.
-
Trust is built through relevant communication: The study found that personalized explanations enhanced "trust in the system" and user "confidence," suggesting that responsible AI deployment should consider not just what information is explained, but how it's presented based on individual user characteristics.
-
Practical implications for AI design: The findings suggest that responsible AI systems should move beyond generic explanations toward adaptive interfaces that recognize individual differences, potentially improving both user understanding and acceptance of AI-driven decisions in real-world applications.
Abstract
Tailoring XAI methods to individual needs is crucial for intuitive Human-AI interactions. While context and task goals are vital, factors like user personality traits could also influence method selection. Our study investigates using personality traits to predict user preferences among decision trees, texts, and factor graphs. We trained a Machine Learning model on responses to the Big Five personality test to predict preferences. Deploying these predicted preferences in a navigation game (n=6), we found users more receptive to personalized XAI recommendations, enhancing trust in the system. This underscores the significance of customization in XAI interfaces, impacting user engagement and confidence.