Abstract
Travelling and touring are popular leisure activities enjoyed by millions of tourists around the world. However, the task of travel itinerary recommendation and planning is tedious and challenging for tourists, who are often unfamiliar with the various Points-of-Interest (POIs) in a city. Apart from identifying popular POIs, the tourist needs to construct a travel itinerary comprising a subset of these POIs, and to order these POIs as a sequence of visits that can be completed within his/her available touring time. For a more realistic itinerary, the tourist also has to account for travelling time between POIs and visiting times at individual POIs. Furthermore, this itinerary should incorporate tourist preferences such as desired starting and ending POIs (e.g., POIs that are near the tourist's hotel) and a subset of must-see POIs (e.g., popular POIs that a tourist must visit). We term this the TourMustSee problem, which is based on a variant of the Orienteering problem. Following which, we propose the LP+M algorithm for solving the TourMustSee problem as an Integer Linear Program (ILP). Using a Flickr dataset of POI visits in seven touristic cities, we compare LP+M against various ILP-based baselines, and the results show that LP+M recommends better travel itineraries in terms of POI popularity, total POIs visited, total touring time utilized and must-visit POI(s) inclusion.