Correlation between digital and physical world, case study in Thessaloniki

Abstract

Abstract This study investigates the use of geo-referenced social media data for enhancing the transportation planning capabilities. A methodological framework is defined for the identification of the citizens’ mobility patterns using social media data, which consists of a number of check-in events that are made through the Facebook service and 1200 taxis’ floating car data for the city of Thessaloniki, during the period of February of 2016. Focus is paid on the derivation of taxi demand forecasting models using the number of check-in events through spatial statistic and analytical tools. The results illustrate the actual correlation of demand for taxis to the check-in events, while it is noted that models should take into account the temporal and spatial offset of the demand production to the check-in events. The results show that the correlation is better during the evening and night hours, since during the morning and afternoon most tips are homework based and people does not check-in at their place of work or at home.