Seven of the most prominent theories Cultural identity is an elusive notion because it depends [3-9] are mapped in Figure 1, showing considerable on a wide range of different cultural factors-- disagreement. For example, in [5] the geographer Wilbur including politics, religion, ethnicity, economics, and art, Zelinsky identified 5 major cultural regions--New England, among countless other examples--which will generally the Midland, the South, the Middle West, and the differ across individuals, with the cultural background West--based on a synthesis of regional patterns in a wide of every individual ultimately being unique. Nevertheless, range of cultural factors, including ethnicity, religion, individuals from the same region can generally be economics, and settlement history. Alternatively, in [6] expected to share some cultural traits, reflecting the drawing on a similar but more extensive range of cultural shared cultural values and practices associated with the factors, the social scientist Raymond Gastil identified 13 region [1]. Identifying the cultural regions of a nation-- major cultural regions, offering a more complex theory regions whose populations are characterized by relative than Zelinsky, including by dividing Zelinsky's Midland, cultural homogeneity compared to the populations of Middle West, and West regions. The two studies illustrate other regions within the nation--is very valuable information two basic limitations with these types of approaches across a wide range of domains. For example, it that subjectively synthesize a range of data to infer cultural is important for governments to understand geographical regions. First, it is unclear exactly how relevant variation in the values of their population so as to cultural factors should be identified. Zelinsky considers better meet their educational, social, and welfare needs.

This paper maps the large-scale variation of the Spanish language by employing a corpus based on geographically tagged Twitter messages. Lexical dialects are extracted from an analysis of variants of tens of concepts. The resulting maps show linguistic variation on an unprecedented scale across the globe. We discuss the properties of the main dialects within a machine learning approach and find that varieties spoken in urban areas have an international character in contrast to country areas where dialects show a more regional uniformity.