Towards Effective, Efficient and Unsupervised Social Event Detection in the Hyperbolic Space

TL;DR

This paper introduces HyperSED, an unsupervised framework that models social messages in hyperbolic space to improve the effectiveness and efficiency of social event detection, outperforming current methods.

Contribution

The work presents a novel unsupervised approach using hyperbolic space and anchor graph structures for social event detection, significantly enhancing performance and efficiency.

Findings

HyperSED improves NMI, AMI, and ARI by 2%, 2%, and 25%.

It increases efficiency by up to 37.41 times.

HyperSED demonstrates competitive performance on public datasets.

Abstract

The vast, complex, and dynamic nature of social message data has posed challenges to social event detection (SED). Despite considerable effort, these challenges persist, often resulting in inadequately expressive message representations (ineffective) and prolonged learning durations (inefficient). In response to the challenges, this work introduces an unsupervised framework, HyperSED (Hyperbolic SED). Specifically, the proposed framework first models social messages into semantic-based message anchors, and then leverages the structure of the anchor graph and the expressiveness of the hyperbolic space to acquire structure- and geometry-aware anchor representations. Finally, HyperSED builds the partitioning tree of the anchor message graph by incorporating differentiable structural information as the reflection of the detected events. Extensive experiments on public datasets demonstrate HyperSED's competitive performance, along with a substantial improvement in efficiency compared to the current state-of-the-art unsupervised paradigm. Statistically, HyperSED boosts incremental SED by an average of 2%, 2%, and 25% in NMI, AMI, and ARI, respectively; enhancing efficiency by up to 37.41 times and at least 12.10 times, illustrating the advancement of the proposed framework. Our code is publicly available at https://github.com/XiaoyanWork/HyperSED.