EventConnector: Mining Social Event Relations through Temporal Graphs

2026-06-13

AI Summary

This study addresses the challenge of effectively modeling instantaneous and directed temporal dependencies among real-world events, a task hindered by existing approaches that rely on semantic similarity or global alignment. To overcome this limitation, the authors propose constructing a temporal event graph to capture local co-fluctuations and lead-lag relationships. They introduce EC-Fusion, a novel mechanism that adaptively integrates graph-structure-based scores with Granger causality signals for precise event association discovery. Evaluated on Polymarket and Kalshi prediction market benchmarks, the method achieves state-of-the-art performance in 17 out of 18 model–dataset combinations, yielding an average RMSE reduction of 6.87% (up to 10.86%), with statistical significance at p < 0.01, thereby demonstrating its effectiveness and innovation.

Abstract

Understanding and retrieving related real-world events based on their temporal dynamics is a fundamental challenge in time-sensitive applications such as forecasting, information retrieval, and social analysis. Existing methods often rely on semantic similarity or global time-series alignment, which overlook the transient and directional dependencies that frequently underlie real-world correlations. In this work, we introduce \textit{EventConnector}, a framework that constructs a temporal event graph capturing localized co-fluctuations and lead-lag relationships between events through their time-series trajectories. We further propose \textbf{EC-Fusion}, an adaptive retrieval mechanism that fuses EventConnector's graph-based scores with a complementary Granger-causal signal via a graph-quality-aware mixing weight. Across two real-world prediction market benchmarks (Polymarket and Kalshi) and nine forecasting architectures evaluated over three random seeds, EC-Fusion is the best non-oracle retrieval method on $17/18$ model--dataset cells, reducing RMSE by $6.87\%$ on average (up to $10.86\%$) over the strongest comparable retrieval baseline, with statistical significance at $p < 0.01$ after Holm--Bonferroni correction. These results highlight the effectiveness of temporally grounded graph modeling, augmented with causal-signal fusion, in capturing latent event relationships beyond what semantic similarity or traditional alignment techniques can offer.

Problem

• temporal event relations
• social events
• time-series trajectories
• lead-lag relationships
• event correlation

Innovation

• Temporal Event Graph
• Lead-Lag Relationships
• Granger Causality
• Adaptive Retrieval
• EC-Fusion