Key points are not available for this paper at this time.
Traffic jam is a contemporary society problem in urban areas. There are specific sources of information about traffic conditions in the Web, such as Bing Maps. This system presents real-time information about the traffic conditions (e.g., free or congested). Recently, participatory sensing systems, such as Foursquare and Instagram, are becoming very popular. Data shared in these systems have the active participation of users using their portable devices ubiquitously. In this case, these systems can be seen as a kind of sensor network, where users can be considered a social sensor, because the data shared by them are associated with their habits and routines. Thus, can we use data from social sensors, specifically from Foursquare and Instagram, to better understand traffic conditions? This paper shows that data from social sensors and traffic conditions, provided by Bing Maps, are surprisingly very correlated. The social data distribution is equal to the traffic condition distribution, shifted by an offset that can be easily calculated. This information can be extremely valuable, for example, to build more efficient traffic condition predictors.
Ribeiro et al. (Wed,) studied this question.