Multi-Order Hyperbolic Graph Convolution and Aggregated Attention for Social Event Detection

TL;DR

This paper introduces MOHGCAA, a novel hyperbolic graph convolution framework with aggregated attention, significantly improving social event detection by capturing multi-order relationships in hierarchical data.

Contribution

The paper proposes a new multi-order hyperbolic graph convolution method with aggregated attention, addressing limitations of existing approaches in social event detection.

Findings

Significant performance improvements in supervised and unsupervised settings.

Effective in capturing complex hierarchical relationships in social event data.

Validated across multiple datasets showing robustness and superiority.

Abstract

Social event detection (SED) is a task focused on identifying specific real-world events and has broad applications across various domains. It is integral to many mobile applications with social features, including major platforms like Twitter, Weibo, and Facebook. By enabling the analysis of social events, SED provides valuable insights for businesses to understand consumer preferences and supports public services in handling emergencies and disaster management. Due to the hierarchical structure of event detection data, traditional approaches in Euclidean space often fall short in capturing the complexity of such relationships. While existing methods in both Euclidean and hyperbolic spaces have shown promising results, they tend to overlook multi-order relationships between events. To address these limitations, this paper introduces a novel framework, Multi-Order Hyperbolic Graph Convolution with Aggregated Attention (MOHGCAA), designed to enhance the performance of SED. Experimental results demonstrate significant improvements under both supervised and unsupervised settings. To further validate the effectiveness and robustness of the proposed framework, we conducted extensive evaluations across multiple datasets, confirming its superiority in tackling common challenges in social event detection.