@article{18856,
  abstract     = {This research is aimed to solve the tweet/user geolocation prediction task and provide a flexible methodology for the geo-tagging of textual big data. The suggested approach implements neural networks for natural language processing (NLP) to estimate the location as coordinate pairs (longitude, latitude) and two-dimensional Gaussian Mixture Models (GMMs). The scope of proposed models has been finetuned on a Twitter dataset using pretrained Bidirectional Encoder Representations from Transformers (BERT) as base models. Performance metrics show a median error of fewer than 30 km on a worldwide-level, and fewer than 15 km on the US-level datasets for the models trained and evaluated on text features of tweets' content and metadata context. Our source code and data are available at https://github.com/K4TEL/geo-twitter.git.},
  author       = {Lutsai, Kateryna and Lampert, Christoph},
  issn         = {1948-660X},
  journal      = {Journal of Spatial Information Science},
  number       = {29},
  pages        = {69--99},
  publisher    = {University of Maine},
  title        = {{Predicting the geolocation of tweets using transformer models on customized data}},
  doi          = {10.5311/JOSIS.2024.29.295},
  year         = {2024},
}

