Scaling up the mining of semantically-enriched trajectories: TripBuilder at the world level

TripBuilder is an unsupervised system helping tourists to build their own personalized sightseeing tour [1, 3, 2]. Given a target touristic city, the time available for the visit, and the tourist's profile, TripBuilder provides a time-budgeted tour that maximizes tourist's interests and takes into account both the time needed to enjoy the at- tractions and to move from one Point of Interest (PoI) to the next one. The knowledge base feeding the sightseeing tour generation algorithm of TripBuilder is entirely mined from publicly available sources, namely, Wikipedia, Flickr and Google Maps. This paper introduces a scalable and robust Cloud architecture (combining both stream and batch processing) to download the data from the heterogeneous sources and build a huge TripBuilder knowledge base covering most popular cities worldwide.