PITAGORA is a mobile web contextual social network designed for the check-in area of an air-port. The app provides recommendation of potential friends, local experts and targeted services. Recommendation is hybrid and combines social media analysis and collaborative ﬁltering techniques. Users’ recommendation has been evaluated through a user study with good results.
The system will be presented at ACM Multimedia 2015, Brisbane, Australia in the Demos Track.
PITAGORA has been developed as a mobile web application available in the check-in area of an airport. The goal of the application is to improve passengers experience providing an enhanced people recommender by exploiting situational information.
The application allows the user to search and display ﬂight infos, to check the presence of passengers on his same ﬂight and to communicate with them through a realtime chat.
Recommendations are mainly constituted by suggestions of other users who share the same interests. Users are also provided with a recommendation of local experts, present at the airport, on the basis of their flight destination. The system uses an hybrid approach to the recommendation problem combining content-based and collaborative filtering. As well-known in literature hybrid approaches give better results solving issues related to the large amount and the sparsity of the data.
The system started as a project developed by the students Andrea Benericetti and Marco Guiducci as final work for the Bachelor of Art at the Faculty of Engineering of University of Florence under the supervision of prof. Alberto Del Bimbo, and his assistants Andrea Ferracani and Daniele Pezzatini.