Automatic identification of urban functions via social mining

Social network users upload billions of geo-referenced data daily, such as photos, videos, and descriptions. While sharing the users' daily moments, these contents can provide distributed and, compared to traditional collections, real-time insights into the interactions between humans and the territory. This paper presents a new methodology to leverage geo-referenced data, linking latent technology data to the municipalities' need for feedback and guidance on past and new investments supporting urban function identification via unsupervised algorithms. We propose a 3-step data-driven pipeline. In the first step, we collect geotagged images posted on Flickr and Instagram and treat them as points on a map. Then, through clustering techniques, we explore a city's geographic contours and investigate how the users' interaction with the city evolved. Eventually, we exploit classification tools to determine what primarily characterizes the city areas. The pipeline, which can be generalized to any geographical area at any level of detail, is verified for the city of Turin through peak detection and zoning tasks. The results demonstrate that the pipeline's outcomes are coherent with the city's traditional characterizations and that social data can provide valid support for the urban experts' analysis.