framework for estimating a Twitter user’s city-level location based purely on the content of the user’s tweets, even in the absence of any other geospatial cues. The content-based approach relies on two key refinements: (i) a classification component for automatically identifying words in tweets with a strong local geo-scope; and (ii) a lattice-based neighborhood smoothing model for refining a user’s location estimate. We have seen how the location estimator can place 51% of Twitter users within 100 miles of their actual location.