SPARQL querying for validating the usage of automatically georeferenced social media data as human sensors for air quality

The problem of air pollution is one of the countless topics discussed on social media on an everyday basis. This rich, crowdsourced information can be exploited to assess the air quality of urban areas, using humans as sensors. Nevertheless, the majority of social media data are falsely geotagged or completely lack geoinformation, which is an essential attribute, while the reliability of the air pollution events reported by online citizens has to be proven. The scope of this work is to present a framework that collects Twitter messages in German that refer to the atmosphere, automatically georeferences them, and finally validates them through semantic representation and SPARQL queries in order to associate them with real measurements of air quality sensors. The georeferencing models are evaluated against state-of-the-art works and the proposed framework is validated in a near-six-month scenario in Germany.