首页 > AI前沿 > STAGE: Spatio-Temporal Augmented Graph Expansion for Weakly Supervised Cross-Tweet Event Causality Discovery

STAGE: Spatio-Temporal Augmented Graph Expansion for Weakly Supervised Cross-Tweet Event Causality Discovery

arXiv自然语言 2026-11-19 23:28 15 阅读 查看原文

研究背景与框架提出

Causal relations in disaster-related social media of- ten span independent posts, making cross-tweet causal discovery difficult to supervise and model at scale. We propose STAGE, a framework that separates scalable cross-tweet weak-supervision construction from spatio-temporal relational learning over event occurrences.

方法实现

Starting from local causal seeds, STAGE retrieves semantically related event occurrences across tweets and uses a causal scorer to construct weakly labeled cross-tweet pairs. These pairs supervise a multi-head Graph Attention Network over semantically enriched event representations and a spatio- temporal context graph.

实验评估

We evaluate STAGE on California Wildfire and Hurricane Harvey using human-gold cross-tweet test sets and 15 baselines. Compared with local-only supervision, the constructed cross-tweet supervision improves STAGE AUPRC by 0.340 on Wildfire and 0.107 on Hurricane. STAGE achieves in-domain AUROC of 0.885 on Wildfire and 0.710 on Hurricane.

实验结果与结论

Cross-disaster experiments reveal asymmetric transfer, highlighting sensitivity to dataset-specific spatio-temporal shifts. These results demonstrate the value of scalable cross-tweet supervision combined with relational event modeling for causal learning across fragmented disaster reports.