This paper is supported by the Special Doctoral Grant of the Ministry of Education of China （No. 98049114） and the National Natural Science Foundation of China （No. 49972023）.
Abstract Instagram is a popular photo-sharing social ap- plication. It is widely used by tourists to record their journey information such as location, time and interest. Consequently, a huge volume of get-tagged phot...Abstract Instagram is a popular photo-sharing social ap- plication. It is widely used by tourists to record their journey information such as location, time and interest. Consequently, a huge volume of get-tagged photos with spatio-temporal in- formation are generated along tourist＇s travel trajectories. Such Instagram photo trajectories consist of travel paths, travel density distributions, and traveller behaviors, prefer- ences, and mobility patterns. Mining Instagram photo trajec- tories is thus very useful for many mobile and location-based social applications, including tour guide and recommender systems. However, we have not found any work that extracts interesting group-like travel trajectories from Instagram pho- tos asynchronously taken by different tourists. Motivated by this, we propose a novel concept： coterie, which reveals representative travel trajectory patterns hidden in Instagram photos taken by users at shared locations and paths. Our work includes the discovery of （1） coteries, （2） closed co- teries, and （3） the recommendation of popular travel routes based on closed coteries. For this, we first build a statistically reliable trajectory database from Instagram get-tagged pho- tos. These trajectories are then clustered by the DBSCAN method to find tourist density. Next, we transform each raw spatio-temporal trajectory into a sequence of clusters. All dis- criminative closed coteries are further identified by a Cluster- Growth algorithm. Finally, distance-aware and conformity- aware recommendation strategies are applied on closed co- teries to recommend popular tour routes. Visualized demosand extensive experimental results demonstrate the effective- ness and efficiency of our methods.展开更多
基金This paper is supported by the Special Doctoral Grant of the Ministry ofEducation of China(No.98049114)and the National Natural Science Foundation of China(No.49972023).
文摘This paper is supported by the Special Doctoral Grant of the Ministry of Education of China （No. 98049114） and the National Natural Science Foundation of China （No. 49972023）.
文摘Abstract Instagram is a popular photo-sharing social ap- plication. It is widely used by tourists to record their journey information such as location, time and interest. Consequently, a huge volume of get-tagged photos with spatio-temporal in- formation are generated along tourist＇s travel trajectories. Such Instagram photo trajectories consist of travel paths, travel density distributions, and traveller behaviors, prefer- ences, and mobility patterns. Mining Instagram photo trajec- tories is thus very useful for many mobile and location-based social applications, including tour guide and recommender systems. However, we have not found any work that extracts interesting group-like travel trajectories from Instagram pho- tos asynchronously taken by different tourists. Motivated by this, we propose a novel concept： coterie, which reveals representative travel trajectory patterns hidden in Instagram photos taken by users at shared locations and paths. Our work includes the discovery of （1） coteries, （2） closed co- teries, and （3） the recommendation of popular travel routes based on closed coteries. For this, we first build a statistically reliable trajectory database from Instagram get-tagged pho- tos. These trajectories are then clustered by the DBSCAN method to find tourist density. Next, we transform each raw spatio-temporal trajectory into a sequence of clusters. All dis- criminative closed coteries are further identified by a Cluster- Growth algorithm. Finally, distance-aware and conformity- aware recommendation strategies are applied on closed co- teries to recommend popular tour routes. Visualized demosand extensive experimental results demonstrate the effective- ness and efficiency of our methods.
