Bridging Cognition and Emotion: Empathy-Driven Multimodal Misinformation Detection

2025-04-24

AI Summary

In the digital era, social media accelerates the dissemination of misinformation, yet conventional detection methods predominantly rely on superficial linguistic or structural features, overlooking the critical role of affective mechanisms. To address this, we propose the Dual-Affection Empathy (DAE) framework—the first to jointly model cognitive and affective empathy from both creator and reader perspectives, enabling an empathy-aware filtering mechanism that enhances response authenticity and diversity. Methodologically, DAE integrates large language models to simulate readers’ cognitive judgments and affective responses, synergizing multimodal features with an empathy-driven reasoning architecture. Extensive experiments across multiple benchmark datasets demonstrate that DAE significantly outperforms state-of-the-art baselines, validating the efficacy, robustness, and cross-domain generalizability of explicit empathy modeling for misinformation detection.

Technology Category

• Natural Language Processing: Fact-Checking / Misinformation Detection (NLP Focus)
• Application Domains: Misinformation & Fake News
• Cognitive Modeling & Cognitive Systems: Affective Computing

Application Category

• Responsible Web: Mitigating misinformation and disinformation
• User Modeling, Personalization and Recommendation: Attacks and countermeasures in recommendation systems
• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics

Abstract

In the digital era, social media has become a major conduit for information dissemination, yet it also facilitates the rapid spread of misinformation. Traditional misinformation detection methods primarily focus on surface-level features, overlooking the crucial roles of human empathy in the propagation process. To address this gap, we propose the Dual-Aspect Empathy Framework (DAE), which integrates cognitive and emotional empathy to analyze misinformation from both the creator and reader perspectives. By examining creators' cognitive strategies and emotional appeals, as well as simulating readers' cognitive judgments and emotional responses using Large Language Models (LLMs), DAE offers a more comprehensive and human-centric approach to misinformation detection. Moreover, we further introduce an empathy-aware filtering mechanism to enhance response authenticity and diversity. Experimental results on benchmark datasets demonstrate that DAE outperforms existing methods, providing a novel paradigm for multimodal misinformation detection.

Problem

• Detect misinformation using cognitive and emotional empathy
• Analyze creator strategies and reader responses with LLMs
• Enhance detection with empathy-aware filtering for authenticity

Innovation

• Integrates cognitive and emotional empathy
• Uses Large Language Models for simulation
• Empathy-aware filtering enhances authenticity