@inproceedings{ljubesic-etal-2016-tweetgeo,
    title = "{T}weet{G}eo - A Tool for Collecting, Processing and Analysing Geo-encoded Linguistic Data",
    author = "Ljube{\v{s}}i{\'c}, Nikola  and
      Samard{\v{z}}i{\'c}, Tanja  and
      Derungs, Curdin",
    editor = "Matsumoto, Yuji  and
      Prasad, Rashmi",
    booktitle = "Proceedings of {COLING} 2016, the 26th International Conference on Computational Linguistics: Technical Papers",
    month = dec,
    year = "2016",
    address = "Osaka, Japan",
    publisher = "The COLING 2016 Organizing Committee",
    url = "https://preview.aclanthology.org/add-emnlp-2024-awards/C16-1322/",
    pages = "3412--3421",
    abstract = "In this paper we present a newly developed tool that enables researchers interested in spatial variation of language to define a geographic perimeter of interest, collect data from the Twitter streaming API published in that perimeter, filter the obtained data by language and country, define and extract variables of interest and analyse the extracted variables by one spatial statistic and two spatial visualisations. We showcase the tool on the area and a selection of languages spoken in former Yugoslavia. By defining the perimeter, languages and a series of linguistic variables of interest we demonstrate the data collection, processing and analysis capabilities of the tool."
}