Learning Behavioral Representations of Human Mobility

TL;DR

This paper introduces mob2vec, a new framework that uses advanced representation learning to analyze human mobility behavior from CDR data, effectively capturing behavioral similarities in low-dimensional vector spaces.

Contribution

The paper presents mob2vec, a novel methodological framework combining noise removal, trajectory generalization, and unsupervised learning for behavioral analysis of mobility data.

Findings

Mob2vec produces low-dimensional vector representations that preserve behavioral similarities.

The framework is validated through extensive experiments on real CDR data.

Results demonstrate improved analysis of human mobility behavior.

Abstract

In this paper, we investigate the suitability of state-of-the-art representation learning methods to the analysis of behavioral similarity of moving individuals, based on CDR trajectories. The core of the contribution is a novel methodological framework, mob2vec, centered on the combined use of a recent symbolic trajectory segmentation method for the removal of noise, a novel trajectory generalization method incorporating behavioral information, and an unsupervised technique for the learning of vector representations from sequential data. Mob2vec is the result of an empirical study conducted on real CDR data through an extensive experimentation. As a result, it is shown that mob2vec generates vector representations of CDR trajectories in low dimensional spaces which preserve the similarity of the mobility behavior of individuals.