Aus Aifbportal
Wechseln zu:Navigation, Suche

A Delay-Robust Touristic Plan Recommendation Using Real-World Public Transportation Information

A Delay-Robust Touristic Plan Recommendation Using Real-World Public Transportation Information

Published: 2017

Buchtitel: Proceedings of the 2nd Workshop on Recommenders in Tourism (RecTour 2017)
Seiten: 9–17
Verlag: CEUR

Referierte Veröffentlichung


Tourism Recommender Systems (TRS) assist tourists in designinga plan for a soon-to-be visited city, which consists of a selectionof relevant points-of-interest (POI), the order in which they willbe visited, the start and end time of the visits, etc. These toolsfilter POIs based on the tourist’s preferences and take into accounttime constraints, like the desired duration of the plan, or the POI’sopening or closing times. However, being able to provide touristswith an additional travel plan which explains how to reach thosePOIs using public transportation is a feature in which TRSs comeshort. Existing solutions try to solve the problem in a simplifiedway and do not model all possible events involved in using publictransportation, such as combining transfer times and trips, changingvehicles, or dealing with delays of transportation units. We thereforepropose three novel approaches to generate visit plans and theircorresponding travel plans, namely SILS, TRILS and PHILS, whichovercome these weaknesses. These approaches generate visit plansby iteratively adjusting them according to the traveling informationand differ in the way the adjustment is done. Our experiments ona real-world POI dataset and public transportation information ofthe city of Izmir show that our approaches outperform the state-of-the-art in terms of quality of recommendations. Moreover, theyare also able to provide both visit and travel plans in real-time andare robust in case of delays. To the best of our knowledge previousapproaches have not been able to achieve this level of practicality.

Download: Media:DelayRobust_RecTour2017.pdf
Weitere Informationen unter: Link


Web Science


Skalierbares Data Mining, Künstliche Intelligenz