Refine
Year of publication
- 2014 (1)
Document Type
Language
- English (1)
Has Fulltext
- yes (1)
Is part of the Bibliography
- no (1)
Keywords
- Dialekt (1)
- Korpus <Linguistik> (1)
- Soziale Medien (1)
- corpus linguistics (1)
- dialect (1)
- social media (1)
Institute
We present a first attempt at classifying German tweets by region using only the text of the tweets. German Twitter users are largely unwilling to share geolocation data. Here, we introduce a two-step process. First, we identify regionally salient tweets by comparing them to an "average" German tweet based on lexical features. Then, regionally salient tweets are assigned to one of 7 dialectal regions. We achieve an accuracy (on regional tweets) of up to 50% on a balanced corpus, much improved from the baseline. Finally, we show several directions in which this work can be extended and improved.
