When Cognitive Graphs Meet LLMs: BDEI Cognitive Pathways for Panic Emotional Arousal Prediction

2026-06-13

AI Summary

This study addresses the challenge of accurately predicting the onset timing of individual panic responses, a task hindered by existing methods’ failure to explicitly model the emotion arousal process. Drawing on appraisal theories of emotion, the authors propose a Belief–Desire–Emotion–Intention (BDEI) cognitive pathway that integrates these four components and introduces, for the first time, an explicit emotion node within a cognitive architecture. A psychological safety distance model is employed to unify multidimensional threat signals, while large language models are deliberately restricted to parameter estimation in the belief-to-desire transformation stage to mitigate hallucination propagation. Evaluated on the Hurricane Sandy dataset, the proposed approach improves prediction accuracy of emotion arousal timing by 10.68% and reduces peak panic population forecasting error to 7.07%.

Abstract

Predicting individual panic emotional arousal timing before manifestation is essential for proactive emergency intervention. Existing methods incorporate cognitive elements but none explicitly model the emotional arousal process, making them ill-suited for emotional arousal timing prediction. We argue that grounding prediction in appraisal emotion theory is necessary because it explicitly models this process, but three problems must be solved. (1) Appraisal theory posits that emotion arises from simultaneous evaluation across multiple threat dimensions, yet no prior work fuses these inputs into risk perception. (2) Existing cognitive models lack an Emotion node, decoupling threat appraisal from emotional arousal and forcing emotions to be inferred indirectly from behaviors. (3) Given their generalizable cognitive reasoning, current approaches adopt LLMs as the primary decision-maker, yet overlook the fragility and hallucination-proneness of their outputs. To address these issues, we introduce PanicCognitivePath (PCP), a framework that addresses all three. A Psychological Safety Distance (PSD) model, grounded in psychological distance theory, maps four-domain signals into a unified risk metric as the entry condition for subsequent cognitive reasoning. An explicit Emotion node grounded in appraisal emotion theory is introduced into BDI, forming a Belief-Desire-Emotion-Intention (BDEI) pathway. Agents whose risk metric exceeds the PSD threshold enter this pathway, coupling threat appraisal directly to emotional arousal. The BDEI pathway governs all state transitions while the LLM is confined to parameter estimation for the Belief-to-Desire transition, confining hallucinations to a single step and preventing error propagation. Experiments on Hurricane Sandy show PCP improves arousal timing accuracy by 10.68% over baselines, reduces peak count error to 7.07%.

Problem

• emotional arousal prediction
• appraisal theory
• cognitive modeling
• LLM hallucination
• panic emotion

Innovation

• Cognitive Graph
• Appraisal Theory
• BDEI Architecture
• Psychological Safety Distance
• LLM Hallucination Mitigation