# A Hierarchical Location Prediction Neural Network for Twitter User Geolocation

arXiv: https://arxiv.org/abs/1910.12941 · HTML: https://mlsanity.com/paper/1910.12941/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 28 Oct 2019.

## Built on by (most cited first, 11 of 11)

- [Unveiling the Truth and Facilitating Change: Towards Agent-based Large-scale Social Movement Simulation](https://mlsanity.com/paper/2402.16333/) (2024)
- [A Transformer-based Framework for POI-level Social Post Geolocation](https://mlsanity.com/paper/2211.01336/) (2022)
- [PolicySim: An LLM-Based Agent Social Simulation Sandbox for Proactive Policy Optimization](https://mlsanity.com/paper/2603.19649/) (2026)
- [Graph Neural Networks: a bibliometrics overview](https://mlsanity.com/paper/2201.01188/) (2022)
- [Analysis of Twitter Users' Lifestyle Choices using Joint Embedding Model](https://mlsanity.com/paper/2104.03189/) (2021)
- [Twitter User Representation Using Weakly Supervised Graph Embedding](https://mlsanity.com/paper/2108.08988/) (2021)
- [Where on Earth Do Users Say They Are?: Geo-Entity Linking for Noisy Multilingual User Input](https://mlsanity.com/paper/2404.18784/) (2024)
- [Designing weighted and multiplex networks for deep learning user geolocation in Twitter](https://mlsanity.com/paper/2112.06999/) (2021)
- [Predicting the Geolocation of Tweets Using transformer models on Customized Data](https://mlsanity.com/paper/2303.07865/) (2023)
- [FewUser: Few-Shot Social User Geolocation via Contrastive Learning](https://mlsanity.com/paper/2404.08662/) (2024)
- [Modeling Social Dynamics with an LLM-Enabled Agent Based Network-Dynamic (LAND) Model](https://mlsanity.com/paper/2608.00929/) (2026)

## Abstract (arXiv)

Accurate estimation of user location is important for many online services. Previous neural network based methods largely ignore the hierarchical structure among locations. In this paper, we propose a hierarchical location prediction neural network for Twitter user geolocation. Our model first predicts the home country for a user, then uses the country result to guide the city-level prediction. In addition, we employ a character-aware word embedding layer to overcome the noisy information in tweets. With the feature fusion layer, our model can accommodate various feature combinations and achieves state-of-the-art results over three commonly used benchmarks under different feature settings. It not only improves the prediction accuracy but also greatly reduces the mean error distance.