[Back]

H. Huang, G. Gartner:
"Learning from Location Histories for Context-aware Location Recommendations in LBS";
Talk: 10th International Symposium on Location-Based Services LBS 2013, Shanghai, China; 11-21-2013 - 11-22-2013; in: "Proceedings of the 10th International Symposium on Location Based Services", (2013), 3 pages.

Location recommendation is one of the most important components in many Location Based Services (LBS), especially in mobile guides. Currently, providing context-aware location (e.g., Point of Interest, POI) recommendations is still very challenging. This paper investigates how human location histories (e.g., GPS trajectories and trajectories constructed from Flickr photos) and collaborative filtering (CF) can be integrated in LBS to provide users with context-aware location recommendations. Evaluation with three real-world location history datasets shows that the proposed solution is feasible and useful for providing context-aware POI recommendations in LBS. With the proposed solution, smart services like "in similar contexts, other people similar to you often went to ..." can be provided in LBS.

Context-aware Recommendations, Location History, Collaborative Filtering