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

AAAI 2022 pp. 12999-13000

doi:10.1609/AAAI.V36I11.21636 /aaai/2022/li2022aaai-geotagging/

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.

PDF AAAI Semantic Scholar

Cite

Text

Li and Lim. "Geotagging Social Media Posts to Landmarks Using Hierarchical BERT (Student Abstract)." AAAI Conference on Artificial Intelligence, 2022. doi:10.1609/AAAI.V36I11.21636

Markdown

[Li and Lim. "Geotagging Social Media Posts to Landmarks Using Hierarchical BERT (Student Abstract)." AAAI Conference on Artificial Intelligence, 2022.](https://mlanthology.org/aaai/2022/li2022aaai-geotagging/) doi:10.1609/AAAI.V36I11.21636

BibTeX

@inproceedings{li2022aaai-geotagging,
  title     = {{Geotagging Social Media Posts to Landmarks Using Hierarchical BERT (Student Abstract)}},
  author    = {Li, Menglin and Lim, Kwan Hui},
  booktitle = {AAAI Conference on Artificial Intelligence},
  year      = {2022},
  pages     = {12999-13000},
  doi       = {10.1609/AAAI.V36I11.21636},
  url       = {https://mlanthology.org/aaai/2022/li2022aaai-geotagging/}
}