The availability of content constantly generated within theWeb has resulted in an incredibly rich virtual social environment from which it is possible to retrieve almost any sort of information. Since the advent of the social media connection with location-based services, this information has attracted the interest of manifold disciplines connected to the spatial data science. In this context, we introduce the URBAN-GEO BIG DATA (URBAN GEOmatics for Bulk Information Generation, Data Assessment and Technology Awareness), a Project of National Interest funded by the Italian Ministry of Education that aims at contributing to the exploitation of heterogeneous geodata sources such as VGI, geo-crowdsourcing, earth observation, etc. for a better understanding of urban dynamics. The presented work tackles one of the tasks requested by the project, which is connected to an investigation of the use of Twitter as a geodata source for retrieving valuable insights on the citizens’ interaction with mobility services and hubs. The study refers to five Italian cities, namely Milan, Turin, Padua, Rome, and Naples. Data collection is performed through the use of the Twitter streaming application programming interface. Collected data is analyzed by means of natural language processing techniques with Python. Results include a) extractions of mobility-related tweets presented by means of maps enabling the exploration of their spatial distribution within the cities, and b) a classification of the mobility-related tweets by means of sentiment analysis, allowing to investigate citizens’ perceptions of mobility services. A light and reproducible procedure to achieve these results is also outlined. In general terms, the results are intended for providing snapshots of the citizen interaction with both mobility infrastructure and services enabling a better description of mobility patterns and habits within the studied cities. The work leverages the geo-crowdsourced data within the traditional urban management practices in Italy and investigates the benefits, drawbacks, limitations connected to these data sources, which is the ultimate goal of the URBAN-GEO BIG DATA project.