MARC: a robust method for multiple-aspect trajectory classification via space, time, and semantic embeddings

The increasing popularity of Location-Based Social Networks (LBSNs) and the se- mantic enrichment of mobility data in several contexts in the last few years has led to the generation of large volumes of trajectory data. In contrast to GPS-based trajec- tories, LBSN and context-aware trajectories are more complex data, having several semantic textual dimensions besides space and time, which may reveal interesting mobility patterns. For instance, people may visit different places or perform differ- ent activities depending on the weather conditions and their geographical location. Animals may choose their habitat based on climate and vegetation characteristics. These new semantically rich data, known as multiple-aspect trajectories, pose new challenges in trajectory classification, which is the problem that we address in this paper. Existing methods for trajectory classification cannot deal with the complexity of heterogeneous data dimensions or the sequential aspect that characterizes move- ment. In this paper we propose MARC, an approach based on attribute embedding and Recurrent Neural Networks (RNNs) for classifying multiple-aspect trajecto- ries, that tackles all trajectory properties: space, time, semantics, and sequence. We highlight that MARC exhibits good performance especially when trajectories are de- scribed by several textual/categorical attributes. Experiments performed over four publicly available datasets considering the Trajectory-User Linking (TUL) prob- lem show that MARC outperformed all competitors in all datasets, with respect to accuracy, precision, recall, and F1-score.