Similarity-based probabilistic category-based location recommendation utilizing temporal and geographical influence

Location recommendation on location-based social networks, which is a rapidly growing research topic, suggests recommendations for unvisited locations to their users. This recommendation service is based on users’ visit histories and location-related information, such as location categories. Finding similarities in users’ behaviors can help these networks make better recommendations. In this paper, we propose two similarity-based Probabilistic Category-based Location Recommendation (sPCLR) algorithms that recommend locations to users at a given time of the day by utilizing category information: sPCLR-DTW and sPCLR-BCC. Both algorithms utilize temporal and spatial components. The temporal component utilizes the temporal influence of similar users’ check-in behaviors by representing users’ periodic check-in behavior at different location categories as temporal curves. The similarity between users’ periodic check-in behavior is calculated based on the difference between temporal curves. In sPCLR-DTW, the traditional dynamic time warping method (DTW) is used to measure the distance between temporal curves. In order to improve the time efficiency of the recommendation process, a novel sequence-matching technique—best curve coupling (BCC)—is proposed and utilized in sPCLR-BCC. The spatial component utilizes the geographical influence of locations and filters out those locations that are not of interest to the user. The performance of the sPCLR-DTW and sPCLR-BCC algorithms are studied and compared to two existing location recommendation algorithms on a real-world dataset. Experimental results show that the sPCLR-DTW performs better than all other recommendation algorithms, whereas sPCLR-BCC can provide comparable recommendations more quickly, making it ideal for online applications.