@inproceedings{salehi-etal-2017-huntsville,
    title = "Huntsville, hospitals, and hockey teams: Names can reveal your location",
    author = "Salehi, Bahar  and
      Hovy, Dirk  and
      Hovy, Eduard  and
      S{\o}gaard, Anders",
    editor = "Derczynski, Leon  and
      Xu, Wei  and
      Ritter, Alan  and
      Baldwin, Tim",
    booktitle = "Proceedings of the 3rd Workshop on Noisy User-generated Text",
    month = sep,
    year = "2017",
    address = "Copenhagen, Denmark",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/jlcl-multiple-ingestion/W17-4415/",
    doi = "10.18653/v1/W17-4415",
    pages = "116--121",
    abstract = "Geolocation is the task of identifying a social media user`s primary location, and in natural language processing, there is a growing literature on to what extent automated analysis of social media posts can help. However, not all content features are equally revealing of a user`s location. In this paper, we evaluate nine name entity (NE) types. Using various metrics, we find that GEO-LOC, FACILITY and SPORT-TEAM are more informative for geolocation than other NE types. Using these types, we improve geolocation accuracy and reduce distance error over various famous text-based methods."
}