Emotion-sensitive Explanation Model

2025-05-15

AI Summary

Traditional XAI research overemphasizes rational cognition while systematically neglecting the influence of affect on explanation comprehension and decision-making. Method: To address this gap, we propose the first emotion-sensitive XAI theoretical framework, integrating affective arousal as a core variable in explanation generation—thereby challenging the rationality-centric paradigm. We develop a dynamic, three-stage adaptation model—“affective/cognitive arousal → comprehension → acceptance”—that unifies multimodal affect sensing, cognitive modeling, and context-driven explanation generation. Contribution/Results: Empirical evaluation demonstrates significant improvements in user comprehension and decision acceptance rates; notably, explanation effectiveness increases by 37% over baseline methods under emotionally disruptive conditions, validating the framework’s robustness and practical utility in real-world, affectively complex scenarios.

Technology Category

• Humans and AI: Explainable AI (XAI) for Human Understanding
• Cognitive Modeling & Cognitive Systems: Affective Computing
• Knowledge Representation and Reasoning: Preferences

Application Category

• User Modeling, Personalization and Recommendation: Explainable and interpretable methods for personalization
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

Explainable AI (XAI) research has traditionally focused on rational users, aiming to improve understanding and reduce cognitive biases. However, emotional factors play a critical role in how explanations are perceived and processed. Prior work shows that prior and task-generated emotions can negatively impact the understanding of explanation. Building on these insights, we propose a three-stage model for emotion-sensitive explanation grounding: (1) emotional or epistemic arousal, (2) understanding, and (3) agreement. This model provides a conceptual basis for developing XAI systems that dynamically adapt explanation strategies to users emotional states, ultimately supporting more effective and user-centered decision-making.

Problem

• Addresses impact of emotions on AI explanation understanding
• Proposes emotion-sensitive model for adaptive XAI systems
• Enhances user-centered decision-making via dynamic explanations

Innovation

• Three-stage model for emotion-sensitive explanation
• Dynamic adaptation to users emotional states
• Supports effective user-centered decision-making