Jonghyun Han and Hyunju Lee (2015) Adaptive Landmark Recommendations for Travel Planning: Personalizing and Clustering Landmarks using Geo-Tagged Social Media. Pervasive and Mobile Computing. 18:4-17 (IF: 2.079) (COMPUTER SCIENCE, NFORMATION SYSTEMS: 20/139)

Adaptive Landmark Recommendations for Travel Planning: Personalizing and Clustering Landmarks using Geo-Tagged Social Media. Pervasive and Mobile Computing.

  • Author : Jonghyun Han and Hyunju Lee
  • Published Date : 2014
  • Category : Mining in Social Network
  • Place of publication : Pervasive and Mobile Computing

 

Abstract

When travelers plan their trips, landmark recommendation systems considering the properties of their trips will be convenient to help travelers determine locations they will visit. Because interesting content may vary according to travelers and their situations, it is important to recommend personalized landmarks by considering them and their trips. In this paper, we propose an approach that adaptively recommends clusters of landmarks using geo-tagged social media. We first examine the impact of spatial and temporal properties of a trip on the distribution of popular places through large-scale data analysis. Our approach is to compute the significance of landmarks for travelers according to the spatial and temporal properties of their trips. Then, we generate clusters of recommended landmarks, which have similar theme or are contiguous, by utilizing histories of travels’ trajectories. Performances of recommended landmarks by our approach are evaluated against several baseline approaches, showing increased accuracy and satisfaction, compared to the baselines. Through a user study, we also verify that it is applicable to lesser-known places and reflective of local events and seasonal changes. Thus, we expect that the approach is helpful in developing personalized recommendations.

Comments are closed.

Post Navigation