Tweets-Geolocation-Using-Deep-Learning

This repository explores the application of deep learning techniques to the task of geolocating tweets. It includes implementations of various models designed to accurately pinpoint the origin of tweets to specific provinces or states.

The dataset generated to train the models can be found here: https://www.kaggle.com/datasets/marwaelteir/ksageolocatedtweets

This notebook also provides all the details required to train the models: https://www.kaggle.com/code/marwaelteir/tweets-geolocation-using-deep-learning/notebook

This repository includes the .keras files for the six best-performing trained models: https://www.kaggle.com/models/marwaelteir/ksatweetsclassifier/

Publications

@article{elteir2025cost,
  title={Cost-effective time-efficient subnational-level surveillance using Twitter: Kingdom of Saudi Arabia case study},
  author={Elteir, Marwa K},
  journal={Discover Applied Sciences},
  volume={7},
  number={1},
  pages={60},
  year={2025},
  publisher={Springer}
}
@article{elteir2024ksadataset,  
  title =  {Fine-grained Arabic Post (Tweet) Geolocation Prediction Using Deep Learning Techniques},    
  author = {Marwa K. Elteir},
  journal = {MDPI Information},
  volume = {},
  number = {},
  pages = {},
  year = {2025},
  issn = {2078-2489},
  doi = {},
  url = {},
  publisher={MDPI}
}