Mining User Similarity Using Spatial-temporal Intersection

The booming industry of location-based services has accumulated a huge collection of users’ location trajectories and also brings us opportunities and challenges to automatically discover valuable knowledge from these trajectories. In this paper, we investigate the problem of measuring the similarity between users. Such user similarity is significant to individuals, communities and businesses by helping them effectively retrieve the information. To achieve this goal, we firstly propose a storage structure to represent the user’s trajectories, which not only stores the sequence of user’s trajectory, but also stores regions with indexing of trajectories which pass the regions. After that, we give the similarity function between users using the spatialtemporal intersection in regions which are passed by the two users. Finally, we develop a spatial-temporal intersection algorithm to measure user similarity based on the definition and storage structure, and we illustrate the results and performance of the algorithm by extensive experiments.