CaST: Causal Discovery via Spatio-Temporal Graphs in Disaster Tweets

TL;DR

CaST introduces a novel spatio-temporal graph-based framework leveraging large language models to uncover causal relationships in disaster-related social media data, improving robustness and interpretability.

Contribution

The paper presents CaST, a unified approach combining semantic, spatial, and temporal information with graph neural networks for causal discovery in disaster tweets, which is a novel integration.

Findings

CaST outperforms traditional and state-of-the-art causal discovery methods.

Incorporating spatial and temporal signals enhances recall and training stability.

The framework effectively models causality in disaster-related social media data.

Abstract

Understanding causality between real-world events from social media is essential for situational awareness, yet existing causal discovery methods often overlook the interplay between semantic, spatial, and temporal contexts. We propose CaST: Causal Discovery via Spatio-Temporal Graphs, a unified framework for causal discovery in disaster domain that integrates semantic similarity and spatio-temporal proximity using Large Language Models (LLMs) pretrained on disaster datasets. CaST constructs an event graph for each window of tweets. Each event extracted from tweets is represented as a node embedding enriched with its contextual semantics, geographic coordinates, and temporal features. These event nodes are then connected to form a spatio-temporal event graph, which is processed using a multi-head Graph Attention Network (GAT) \cite{gat} to learn directed causal relationships. We construct an in-house dataset of approximately 167K disaster-related tweets collected during Hurricane Harvey and annotated following the MAVEN-ERE schema. Experimental results show that CaST achieves superior performance over both traditional and state-of-the-art methods. Ablation studies further confirm that incorporating spatial and temporal signals substantially improves both recall and stability during training. Overall, CaST demonstrates that integrating spatio-temporal reasoning into event graphs enables more robust and interpretable causal discovery in disaster-related social media text.