On the Accuracy of Hyper-local Geotagging of Social Media Content

Social media users share billions of items per year, only a small fraction of which is geotagged. We present a data- driven approach for identifying non-geotagged content items that can be associated with a hyper-local geographic area by modeling the location distributions of hyper-local n-grams that appear in the text. We explore the trade-off between accuracy, precision and coverage of this method. Further, we explore differences across content received from multiple platforms and devices, and show, for example, that content shared via different sources and applications produces significantly different geographic distributions, and that it is best to model and predict location for items according to their source. Our findings show the potential and the bounds of a data-driven approach to geotag short social media texts, and offer implications for all applications that use data-driven approaches to locate content.