@InProceedings{donoso-sanchez:2017:VarDial,
  author    = {Donoso, Gonzalo  and  Sanchez, David},
  title     = {Dialectometric analysis of language variation in Twitter},
  booktitle = {Proceedings of the Fourth Workshop on NLP for Similar Languages, Varieties and Dialects (VarDial)},
  month     = {April},
  year      = {2017},
  address   = {Valencia, Spain},
  publisher = {Association for Computational Linguistics},
  pages     = {16--25},
  abstract  = {In the last few years, microblogging platforms such as Twitter have given rise
	to a deluge of textual data that can be used for the analysis of informal
	communication between millions of individuals. In this work, we propose an
	information-theoretic approach to geographic language variation using a corpus
	based on Twitter. We test our models with tens of concepts and their associated
	keywords detected in Spanish tweets geolocated in Spain. We employ
	dialectometric measures (cosine similarity and Jensen-Shannon divergence) to
	quantify the linguistic distance on the lexical level between cells created in
	a uniform grid over the map. This can be done for a single concept or in the
	general case taking into account an average of the considered variants. The
	latter permits an analysis of the dialects that naturally emerge from the data.
	Interestingly, our results reveal the existence of two dialect macrovarieties.
	The first group includes a region-specific speech spoken in small towns and
	rural areas whereas the second cluster encompasses cities that tend to use a
	more uniform variety. Since the results obtained with the two different metrics
	qualitatively agree, our work suggests that social media corpora can be
	efficiently used for dialectometric analyses.},
  url       = {http://www.aclweb.org/anthology/W17-1202}
}