# FewUser: Few-Shot Social User Geolocation via Contrastive Learning

arXiv: https://arxiv.org/abs/2404.08662 · HTML: https://mlsanity.com/paper/2404.08662/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 16 of its 33 references that are in the map.
- First posted on arXiv 28 Mar 2024.

## Builds on (most cited first, 16 of 16)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Momentum Contrast for Unsupervised Visual Representation Learning](https://mlsanity.com/paper/1911.05722/) (2019)
- [Pre-train, Prompt, and Predict: A Systematic Survey of Prompting Methods in Natural Language Processing](https://mlsanity.com/paper/2107.13586/) (2021)
- [SimCSE: Simple Contrastive Learning of Sentence Embeddings](https://mlsanity.com/paper/2104.08821/) (2021)
- [Align before Fuse: Vision and Language Representation Learning with Momentum Distillation](https://mlsanity.com/paper/2107.07651/) (2021)
- [How Can We Know What Language Models Know?](https://mlsanity.com/paper/1911.12543/) (2019)
- [PointCLIP: Point Cloud Understanding by CLIP](https://mlsanity.com/paper/2112.02413/) (2021)
- [Factual Probing Is [MASK]: Learning vs. Learning to Recall](https://mlsanity.com/paper/2104.05240/) (2021)
- [A Survey of Location Prediction on Twitter](https://mlsanity.com/paper/1705.03172/) (2017)
- [A Transformer-based Framework for POI-level Social Post Geolocation](https://mlsanity.com/paper/2211.01336/) (2022)
- [A Neural Model for User Geolocation and Lexical Dialectology](https://mlsanity.com/paper/1704.04008/) (2017)
- [A Hierarchical Location Prediction Neural Network for Twitter User Geolocation](https://mlsanity.com/paper/1910.12941/) (2019)
- [POIBERT: A Transformer-based Model for the Tour Recommendation Problem](https://mlsanity.com/paper/2212.13900/) (2022)
- [Continuous Representation of Location for Geolocation and Lexical Dialectology using Mixture Density Networks](https://mlsanity.com/paper/1708.04358/) (2017)
- [Twitter User Geolocation using Deep Multiview Learning](https://mlsanity.com/paper/1805.04612/) (2018)
- [Leveraging Contrastive Learning for Few-shot Geolocation of Social Posts](https://mlsanity.com/paper/2403.00786/) (2024)

## Abstract (arXiv)

To address the challenges of scarcity in geotagged data for social user geolocation, we propose FewUser, a novel framework for Few-shot social User geolocation. We incorporate a contrastive learning strategy between users and locations to improve geolocation performance with no or limited training data. FewUser features a user representation module that harnesses a pre-trained language model (PLM) and a user encoder to process and fuse diverse social media inputs effectively. To bridge the gap between PLM's knowledge and geographical data, we introduce a geographical prompting module with hard, soft, and semi-soft prompts, to enhance the encoding of location information. Contrastive learning is implemented through a contrastive loss and a matching loss, complemented by a hard negative mining strategy to refine the learning process. We construct two datasets TwiU and FliU, containing richer metadata than existing benchmarks, to evaluate FewUser and the extensive experiments demonstrate that FewUser significantly outperforms state-of-the-art methods in both zero-shot and various few-shot settings, achieving absolute improvements of 26.95% and 41.62% on TwiU and FliU, respectively, with only one training sample per class. We further conduct a comprehensive analysis to investigate the impact of user representation on geolocation performance and the effectiveness of FewUser's components, offering valuable insights for future research in this area.