Semi-supervised User Geolocation via Graph Convolutional Networks
This addresses geolocation for social media users, which is incremental as it builds on existing GCN methods with specific improvements like highway network gates.
The paper tackles social media user geolocation by proposing a multiview model based on Graph Convolutional Networks (GCN) that uses text and network context, achieving or being competitive with state-of-the-art on three benchmark datasets with sufficient supervision and outperforming baselines under minimal supervision.
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.