Semi-supervised User Geolocation via Graph Convolutional Networks

TL;DR

This paper introduces GCN, a multiview graph convolutional network model that combines text and network context for social media user geolocation, demonstrating competitive and superior performance under various supervision levels.

Contribution

The paper presents a novel GCN-based model for user geolocation that effectively integrates multiple data views and outperforms existing methods, especially with limited supervision.

Findings

GCN achieves or surpasses state-of-the-art accuracy on benchmark datasets.

In minimal supervision scenarios, GCN outperforms baseline models.

Highway network gates are crucial for controlling neighborhood expansion.

Abstract

Social media user geolocation is vital to many applications such as event detection. In this paper, we propose GCN, a multiview geolocation model based on Graph Convolutional Networks, that uses both text and network context. We compare GCN to the state-of-the-art, and to two baselines we propose, and show that our model achieves or is competitive with the state- of-the-art over three benchmark geolocation datasets when sufficient supervision is available. We also evaluate GCN under a minimal supervision scenario, and show it outperforms baselines. We find that highway network gates are essential for controlling the amount of useful neighbourhood expansion in GCN.