Human mobility analysis based on social media and fuzzy clustering

A better understanding of the movement of a city aids to the efficient adaptation of the energy consumption to the necessities of citizens. For this purpose, the use of clustering algorithms applied to large amounts of geo-tagged data generated in social-networks is foreseen to become an interesting course of action. This will help to comprehensively capture and understand the movement of people in large spatial regions. Due to the nature of this kind of data (with high levels of uncertainty and noise) soft-computing owns the necessary characteristics to extract accurate mobility models. The present work introduces a novel approach to extract personal mobility patterns by means of the fuzzy c-means (FCM) algorithm. A preliminary study with a real Twitter database is also included.