Psychology-driven LLM Agents for Explainable Panic Prediction on Social Media during Sudden Disaster Events

• URL: http://arxiv.org/abs/2505.16455v1
• Date: Thu, 22 May 2025 09:39:39 GMT
• Title: Psychology-driven LLM Agents for Explainable Panic Prediction on Social Media during Sudden Disaster Events
• Abstract summary: We propose a Psychology-driven generative Agent framework (PsychoAgent) for explainable panic prediction based on emotion arousal theory.<n>Specifically, we first construct a fine-grained open panic emotion dataset (namely COPE) via human-large language models (LLMs)<n>To enhance interpretability, we design an LLM-based role-playing agent that simulates individual psychological chains through dedicatedly designed prompts.
• Score: 25.69230239224621
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: During sudden disaster events, accurately predicting public panic sentiment on social media is crucial for proactive governance and crisis management. Current efforts on this problem face three main challenges: lack of finely annotated data hinders emotion prediction studies, unmodeled risk perception causes prediction inaccuracies, and insufficient interpretability of panic formation mechanisms. We address these issues by proposing a Psychology-driven generative Agent framework (PsychoAgent) for explainable panic prediction based on emotion arousal theory. Specifically, we first construct a fine-grained open panic emotion dataset (namely COPE) via human-large language models (LLMs) collaboration to mitigate semantic bias. Then, we develop a framework integrating cross-domain heterogeneous data grounded in psychological mechanisms to model risk perception and cognitive differences in emotion generation. To enhance interpretability, we design an LLM-based role-playing agent that simulates individual psychological chains through dedicatedly designed prompts. Experimental results on our annotated dataset show that PsychoAgent improves panic emotion prediction performance by 12.6% to 21.7% compared to baseline models. Furthermore, the explainability and generalization of our approach is validated. Crucially, this represents a paradigm shift from opaque "data-driven fitting" to transparent "role-based simulation with mechanistic interpretation" for panic emotion prediction during emergencies. Our implementation is publicly available at: https://anonymous.4open.science/r/PsychoAgent-19DD.

Related papers

• A Cognition-Emotion-Personality Framework for Modeling Human-Like Awareness and Behavior in Emergency Evacuations [0.0]
  This paper presents an extended evacuation framework that integrates cognitive, emotional, social, and personality-related mechanisms.<n>Results show that cognitive, emotional, and personality-driven processes substantially influence evacuation dynamics.
  arXiv  Detail & Related papers  (2026-06-28T05:39:15Z)
• When Cognitive Graphs Meet LLMs: BDEI Cognitive Pathways for Panic Emotional Arousal Prediction [20.38395886496368]
  Predicting individual panic emotional arousal timing before manifestation is essential for proactive emergency intervention.<n>Existing methods incorporate cognitive elements but none explicitly model the emotional arousal process.<n>We argue that grounding prediction in appraisal emotion theory is necessary because it explicitly models this process.
  arXiv  Detail & Related papers  (2026-06-13T05:23:00Z)
• The Silicon Psyche: Anthropomorphic Vulnerabilities in Large Language Models [0.2291770711277359]
  Large Language Models (LLMs) are rapidly transitioning from conversational assistants to autonomous agents embedded in critical organizational functions.<n>This paper presents the first systematic application of the Cybersecurity Psychology Framework (cpf), a 100-indicator taxonomy of human psychological vulnerabilities, to non-human cognitive agents.
  arXiv  Detail & Related papers  (2025-12-30T13:25:36Z)
• Breaking Minds, Breaking Systems: Jailbreaking Large Language Models via Human-like Psychological Manipulation [6.67891820536196]
  Psychological Jailbreak is an attack paradigm that exposes a stateful psychological attack surface in large language models.<n>Human-like Psychological Manipulation (HPM) profiles a target model's latent psychological vulnerabilities and synthesizes tailored multi-turn attack strategies.<n>HPM achieves a mean Attack Success Rate (ASR) of 88.1%, outperforming state-of-the-art attack baselines.
  arXiv  Detail & Related papers  (2025-12-20T07:02:00Z)
• DeceptionBench: A Comprehensive Benchmark for AI Deception Behaviors in Real-world Scenarios [57.327907850766785]
  characterization of deception across realistic real-world scenarios remains underexplored.<n>We establish DeceptionBench, the first benchmark that systematically evaluates how deceptive tendencies manifest across different domains.<n>On the intrinsic dimension, we explore whether models exhibit self-interested egoistic tendencies or sycophantic behaviors that prioritize user appeasement.<n>We incorporate sustained multi-turn interaction loops to construct a more realistic simulation of real-world feedback dynamics.
  arXiv  Detail & Related papers  (2025-10-17T10:14:26Z)
• ReDepress: A Cognitive Framework for Detecting Depression Relapse from Social Media [48.56586765769052]
  We present ReDepress, the first clinically validated social media dataset focused on relapse.<n>Our framework draws on cognitive theories of depression, incorporating constructs such as attention bias, interpretation bias, memory bias and rumination.<n>Our findings validate psychological theories in real-world textual data and underscore the potential of cognitive-informed computational methods for early relapse detection.
  arXiv  Detail & Related papers  (2025-09-22T16:33:59Z)
• Wrong Face, Wrong Move: The Social Dynamics of Emotion Misperception in Agent-Based Models [2.0221069271989305]
  The ability of humans to detect and respond to others' emotions is fundamental to understanding social behavior.<n>Here, agents are instantiated with emotion classifiers of varying accuracy to study the impact of perceptual accuracy on emergent emotional and spatial behavior.<n>Results show that low-accuracy classifiers reliably result in diminished trust, emotional disintegration into sadness, and disordered social organization.
  arXiv  Detail & Related papers  (2025-08-26T22:42:46Z)
• Before the Outrage: Challenges and Advances in Predicting Online Antisocial Behavior [1.223779595809275]
  Antisocial behavior on social media poses growing challenges for platform safety and societal wellbeing.<n>Prior work has primarily focused on detecting harmful content after it appears, but predictive approaches aim to forecast future harmful behaviors.<n>Despite increasing interest, the field remains fragmented, lacking a unified taxonomy or clear synthesis of existing methods.
  arXiv  Detail & Related papers  (2025-07-28T08:27:58Z)
• Teleology-Driven Affective Computing: A Causal Framework for Sustained Well-Being [0.1636303041090359]
  We propose a teleology-driven affective computing framework that unifies major emotion theories.<n>We advocate for creating a "dataverse" of personal affective events.<n>We introduce a meta-reinforcement learning paradigm to train agents in simulated environments.
  arXiv  Detail & Related papers  (2025-02-24T14:07:53Z)
• Mechanistic Interpretability of Emotion Inference in Large Language Models [16.42503362001602]
  We show that emotion representations are functionally localized to specific regions in large language models.<n>We draw on cognitive appraisal theory to show that emotions emerge from evaluations of environmental stimuli.<n>This work highlights a novel way to causally intervene and precisely shape emotional text generation.
  arXiv  Detail & Related papers  (2025-02-08T08:11:37Z)
• Performative Prediction on Games and Mechanism Design [69.7933059664256]
  We study a collective risk dilemma where agents decide whether to trust predictions based on past accuracy.<n>As predictions shape collective outcomes, social welfare arises naturally as a metric of concern.<n>We show how to achieve better trade-offs and use them for mechanism design.
  arXiv  Detail & Related papers  (2024-08-09T16:03:44Z)
• Emotion-Oriented Behavior Model Using Deep Learning [0.9176056742068812]
  The accuracy of emotion-based behavior predictions is statistically validated using the 2-tailed Pearson correlation. This study is a steppingstone to a multi-faceted artificial agent interaction based on emotion-oriented behaviors.
  arXiv  Detail & Related papers  (2023-10-28T17:27:59Z)
• Learning Theory of Mind via Dynamic Traits Attribution [59.9781556714202]
  We propose a new neural ToM architecture that learns to generate a latent trait vector of an actor from the past trajectories. This trait vector then multiplicatively modulates the prediction mechanism via a fast weights' scheme in the prediction neural network. We empirically show that the fast weights provide a good inductive bias to model the character traits of agents and hence improves mindreading ability.
  arXiv  Detail & Related papers  (2022-04-17T11:21:18Z)
• Are socially-aware trajectory prediction models really socially-aware? [75.36961426916639]
  We introduce a socially-attended attack to assess the social understanding of prediction models. An attack is a small yet carefully-crafted perturbations to fail predictors. We show that our attack can be employed to increase the social understanding of state-of-the-art models.
  arXiv  Detail & Related papers  (2021-08-24T17:59:09Z)
• When a crisis strikes: Emotion analysis and detection during COVID-19 [96.03869351276478]
  We present CovidEmo, 1K tweets labeled with emotions. We examine how well large pre-trained language models generalize across domains and crises.
  arXiv  Detail & Related papers  (2021-07-23T04:07:14Z)
• Heterogeneous-Agent Trajectory Forecasting Incorporating Class Uncertainty [54.88405167739227]
  We present HAICU, a method for heterogeneous-agent trajectory forecasting that explicitly incorporates agents' class probabilities. We additionally present PUP, a new challenging real-world autonomous driving dataset. We demonstrate that incorporating class probabilities in trajectory forecasting significantly improves performance in the face of uncertainty.
  arXiv  Detail & Related papers  (2021-04-26T10:28:34Z)
• AGENT: A Benchmark for Core Psychological Reasoning [60.35621718321559]
  Intuitive psychology is the ability to reason about hidden mental variables that drive observable actions. Despite recent interest in machine agents that reason about other agents, it is not clear if such agents learn or hold the core psychology principles that drive human reasoning. We present a benchmark consisting of procedurally generated 3D animations, AGENT, structured around four scenarios.
  arXiv  Detail & Related papers  (2021-02-24T14:58:23Z)
• Capturing social media expressions during the COVID-19 pandemic in Argentina and forecasting mental health and emotions [0.802904964931021]
  We forecast mental health conditions and emotions of a given population during the COVID-19 pandemic in Argentina based on language expressions used in social media. Mental health conditions and emotions are captured via markers, which link social media contents with lexicons.
  arXiv  Detail & Related papers  (2021-01-12T15:15:31Z)
• Social Media Unrest Prediction during the {COVID}-19 Pandemic: Neural Implicit Motive Pattern Recognition as Psychometric Signs of Severe Crises [26.447165399064552]
  We present psychologically validated social unrest predictors and replicate scalable and automated predictions. We employ this model to investigate a change of language towards social unrest during the COVID-19 pandemic.
  arXiv  Detail & Related papers  (2020-12-08T17:40:35Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.