Complementing Travel Itinerary Recommendation Using Location-Based Social Networks

We proposed in a previous work a recommendation system that, according to the requirements specified by its users, was capable of generating a few travel itineraries of distinct features (e.g. the most appealing itinerary, the shortest itinerary or the itinerary with the highest performance/price ratio) for user selection. We anticipated to complement the recommended travel itineraries by taking advantage of recent advances in location-acquisition and wireless communication technologies. With such technologies, people can share geo-spatial locations and location-based activities in the physical world via location-based social networks (LBSN), which makes it possible to help deduce a prospective traveler's dream destination using their check-ins published and shared on those websites. These user check-ins are informative in that a user's historical behaviors is a powerful indicator of his/her preferences. Therefore, we looked into and utilized user check-ins and social connections when building up a trip planner (such as our recommender) so as to better serve the travelers who may merely wander a travel website and seek the best vacation packages, flights, or hotel for their next trip. Our experiment verified the feasibility and efficiency of using user check-ins and social connections accessible from LBSNs in terms of discovering users' potential travel destination.

[1]  H. Hotelling.  Analysis of a complex of statistical variables into principal components. , 1933 .

[2]  Kevin Chen-Chuan Chang,et al.  A Comprehensive Survey of Graph Embedding: Problems, Techniques, and Applications , 2017, IEEE Transactions on Knowledge and Data Engineering.

[3]  Steven Skiena,et al.  DeepWalk: online learning of social representations , 2014, KDD.

[4]  Leland McInnes,et al.  UMAP: Uniform Manifold Approximation and Projection , 2018, J. Open Source Softw..

[5]  Philip S. Yu,et al.  Collective Geographical Embedding for Geolocating Social Network Users , 2017, PAKDD.

[6]  Jing Zhou,et al.  An Improved Recommender for Travel Itineraries , 2018, Intelligent Information Processing.

[7]  Mohamed F. Mokbel,et al.  Recommendations in location-based social networks: a survey , 2015, GeoInformatica.

[8]  Andrew W. Moore,et al.  X-means: Extending K-means with Efficient Estimation of the Number of Clusters , 2000, ICML.

[9]  Mingzhe Wang,et al.  LINE: Large-scale Information Network Embedding , 2015, WWW.

[10]  Qiaozhu Mei,et al.  PTE: Predictive Text Embedding through Large-scale Heterogeneous Text Networks , 2015, KDD.

[11]  Jing Zhou,et al.  A Recommender for Personalized Travel Itineraries , 2018, ICCCS.

[12]  François Fouss,et al.  Random-Walk Computation of Similarities between Nodes of a Graph with Application to Collaborative Recommendation , 2007, IEEE Transactions on Knowledge and Data Engineering.

[13]  Jure Leskovec,et al.  Friendship and mobility: user movement in location-based social networks , 2011, KDD.

[14]  Geoffrey E. Hinton,et al.  Visualizing Data using t-SNE , 2008 .

[15]  Jeffrey Dean,et al.  Distributed Representations of Words and Phrases and their Compositionality , 2013, NIPS.