Twitter User Geolocation Using a Unified Text and Network Prediction Model
This addresses geolocation prediction for social media users, but it is incremental as it builds on existing methods with specific tweaks.
The paper tackled the problem of predicting Twitter user geolocation by proposing a label propagation approach with enhancements like removing celebrity nodes and incorporating text-based priors, achieving state-of-the-art results on three benchmark datasets.
We propose a label propagation approach to geolocation prediction based on Modified Adsorption, with two enhancements:(1) the removal of "celebrity" nodes to increase location homophily and boost tractability, and (2) he incorporation of text-based geolocation priors for test users. Experiments over three Twitter benchmark datasets achieve state-of-the-art results, and demonstrate the effectiveness of the enhancements.