@inproceedings{SchefflerGontrumWegeletal.2014, author = {Tatjana Scheffler and Johannes Gontrum and Matthhias Wegel and Steve Wendler}, title = {Mapping German Tweets to Geographic Regions}, isbn = {978-3-934105-47-8}, url = {https://nbn-resolving.org/urn:nbn:de:gbv:hil2-opus-3236}, year = {2014}, abstract = {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.}, language = {en} }