Taking Brazil's pulse: tracking growing urban economies from online attention

Urban resources are allocated according to socio-economic indicators, and rapid urbanization in developing countries calls for updating those indicators in a timely fashion. The prohibitive costs of census data collection make that very difficult. To avoid allocating resources upon outdated indicators, one could partly update or complement them using digital data. It has been shown that it is possible to use social media in developed countries (mainly UK and USA) for such a purpose. Here we show that this is the case for Brazil too. We analyze a random sample of a microblogging service popular in that country and accurately predict the GDPs of 45 Brazilian cities. To make these predictions, we exploit the sociological concept of glocality, which says that economically successful cities tend to be involved in interactions that are both local and global at the same time. We indeed show that a city's glocality, measured with social media data, effectively signals the city's economic well-being.