Complete User Mobility via User and Trajectory Embeddings

Nowadays, human movements are recorded with a variety of tools, forming different trajectorysets which are usually isolated from each other. These isolated trajectories come from different tools such as Twitter, Facebook, and so on that are related to one individual. Thus, it is important to link trajectories to users who generate them in order to provide massive information for facilitating trajectory mining tasks. Most previous work took advantage of trajectory similarities or trajectory classification models to solve this problem. However, these methods ignored the users' movement patterns, which play a critical role in mining information from these users' trajectories. In this paper, we propose a novel approach called trajectory linking via user embedding and trajectory embedding to learn the movement patterns of users and trajectories simultaneously, and use those movement patterns to link trajectories to users. More specifically, we leverage a graph-based location embedding method to learn the semantics of locations based on categorical and spatial information of locations. Then, a novel dual-objective neural network model is designed to integrate the sequential dependency and temporal regularity of trajectories to learn the movement patterns of users and their trajectories at the same time. A trajectory is then linked to the user who has the most similar movement pattern with it. Moreover, the advantages of our approach are empirically verified on real-world public trajectory datasets with convincing results.