Geotagging Social Media Posts to Landmarks Using Hierarchical BERT (Student Abstract)

Authors

  • Menglin Li Singapore University of Technology and Design
  • Kwan Hui Lim Singapore University of Technology and Design

DOI:

https://doi.org/10.1609/aaai.v36i11.21636

Keywords:

Geotagging, Social Media, BERT, Hierarchical Classification

Abstract

Geographical information provided in social media data is useful for many valuable applications. However, only a small proportion of social media posts are explicitly geotagged with their posting locations, which makes the pursuit of these applications challenging. Motivated by this, we propose a 2-level hierarchical classification method that builds upon a BERT model, coupled with textual information and temporal context, which we denote HierBERT. As far as we are aware, this work is the first to utilize a 2-level hierarchical classification approach alongside BERT and temporal information for geolocation prediction. Experimental results based on two social media datasets show that HierBERT outperforms various state-of-art baselines in terms of accuracy and distance error metrics.

Downloads

Published

2022-06-28

How to Cite

Li, M., & Lim, K. H. (2022). Geotagging Social Media Posts to Landmarks Using Hierarchical BERT (Student Abstract). Proceedings of the AAAI Conference on Artificial Intelligence, 36(11), 12999-13000. https://doi.org/10.1609/aaai.v36i11.21636