Annotating trajectories by fusing them with social media users' posts

The widespread use of mobile devices allows gathering large amounts of moving objects' trajectories. However, just trajectories are often not enough to enable movements understanding. On the other hand, users' posts in social media can be regarded as sparse and freely annotated movement traces, which can also be collected via mobile devices. This paper proposes a method for automatically fusing trajectories with social media users' posts based on their spatiotemporal compatibility. The results are trajectories annotated with posts contents, that may help to explain movement goals, and relations with places and events, among other information. The proposed method has been implemented and evaluated in experiments with real GPS trajectories and tweets.