Public transport optimisation is becoming everyday a more di cult and challenging task, because of the increasing number of transportation options as well as the exponential increase of users. Many research contributions about this issue have been recently published under the umbrella of the smart cities research. In this work, we sketch a possible framework to optimize the tourist bus in the city of Barcelona. Our framework will extract information from Twitter and other web services, such as Foursquare to infer not only the most visited places in Barcelona, but also the trajectories and routes that tourist follow. After that, instead of using complex geospatial or trajectory clustering methods, we propose to use simpler clustering techniques as k-means or DBScan but using a real sequence of symbols as a distance measure to incorporate in the clustering process the trajectory information.

This work is partially supported by the Ministry of Science and Technology of Spain under contract TIN2012-34557 and by the BSC-CNSSevero Ochoa program (SEV-2011-00067) and with the support of ACC1Ó, theCatalan Agency to promote applied research and innovation; and by the Spanish Centre for Development of Industrial Technology under the INNPRONTA program, project IPT-20111006, \CIUDAD2020".