Traveling is part of many people leisure activities and an increasing fraction of the economy comes from the tourism. Given a destination, the information about the different attractions, or points of interest (POIs), can be found on many sources. Among these attractions, finding the ones that could be of interest for a specific user represents a challenging task. Travel recommendation systems deal with this type of problems. Most of the solution in the literature does not take into account the impact of the suggestions on the level of crowding of POIs. This paper considers the trip planning problem focusing on user balancing among the different POIs. To this aim, we consider the effects of the previous recommendations, as well as estimates based on historical data, while devising a new recommendation. The problem is formulated as a multi-objective optimization problem, and a recommendation engine has been designed and implemented for exploring the solution space in near real-time, through a distributed version of the Simulated Annealing approach. We test our solution using a real dataset of users visiting the POIs of a touristic city, and we show that we are able to provide high quality recommendations, yet maintaining the attractions not overcrowded.

Distributing Tourists Among POIs with an Adaptive Trip Recommendation System

Migliorini, Sara;Carra, Damiano;Belussi, Alberto
2021-01-01

Abstract

Traveling is part of many people leisure activities and an increasing fraction of the economy comes from the tourism. Given a destination, the information about the different attractions, or points of interest (POIs), can be found on many sources. Among these attractions, finding the ones that could be of interest for a specific user represents a challenging task. Travel recommendation systems deal with this type of problems. Most of the solution in the literature does not take into account the impact of the suggestions on the level of crowding of POIs. This paper considers the trip planning problem focusing on user balancing among the different POIs. To this aim, we consider the effects of the previous recommendations, as well as estimates based on historical data, while devising a new recommendation. The problem is formulated as a multi-objective optimization problem, and a recommendation engine has been designed and implemented for exploring the solution space in near real-time, through a distributed version of the Simulated Annealing approach. We test our solution using a real dataset of users visiting the POIs of a touristic city, and we show that we are able to provide high quality recommendations, yet maintaining the attractions not overcrowded.
2021
trip recommendation
tourist balancing
simulated annealing
MapReduce
SpatialHadoop
File in questo prodotto:
File Dimensione Formato  
00_main.pdf

Open Access dal 07/06/2021

Tipologia: Documento in Post-print
Licenza: Creative commons
Dimensione 4.45 MB
Formato Adobe PDF
4.45 MB Adobe PDF Visualizza/Apri

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11562/995894
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 8
  • ???jsp.display-item.citation.isi??? 5
social impact