Assessing the attractiveness of places with movement data

Attractiveness of places has been studied by several sciences, giving rise to distinct ways for assessing it. However, the attractiveness evaluation methods currently available lack versatility to analyze diverse attractiveness phenomena in different kinds of places and spatial scales. This article describes a novel method, called M-Attract, to assess the attractiveness of interesting places, based on movement data. M-Attract examines trajectory episodes (e.g., stop, pass) that happen in places and their encompassing regions to compute their attractiveness. It is more flexible than state-of-the-art methods, with respect to land parcels, parameters, and measures used for attractiveness assessment. The proposed method has been extensively evaluated in experiments with real data, which demonstrate its contributions to analyze attractiveness of places and identify relevant phenomena in the geographic space.