By absorbing more than 3.4 millions Syrians, Turkey has shown a remarkable resilience. But the host community hostility toward these newcomers is rising. Thus, the formulation of effective integration policies is needed. However, assessing the effectiveness of such policies demands tools able to measure the integration of refugees despite the complexity of such phenomena. In this work, we propose a set of metrics aimed at providing insights and assessing the integration of Syrians refugees, by analyzing the CDR dataset of the challenge. Specifically, we aim at assessing the integration of refugees, by exploiting the similarity between refugees and locals in terms of calling behavior and mobility, considering different spatial and temporal features. Together with the already known methods for data analysis, in this work we use a novel computational approach to analyze users' mobility: computational stigmergy, a bio-inspired scalar and temporal aggregation of samples. Computational stigmergy associates each sample to a virtual pheromone deposit (mark) defined in a multidimensional space and characterized by evaporation over time. Marks in spatiotemporal proximity are aggregated into functional structures called trail. The stigmergic trail summarizes the spatiotemporal dynamics in data and allows to compute the stigmergic similarity between them.
Using Call Data and Stigmergic Similarity to Assess the Integration of Syrian Refugees in Turkey
Antonio Luca Alfeo;Mario G. C. A. Cimino;Gigliola Vaglini
2019-01-01
Abstract
By absorbing more than 3.4 millions Syrians, Turkey has shown a remarkable resilience. But the host community hostility toward these newcomers is rising. Thus, the formulation of effective integration policies is needed. However, assessing the effectiveness of such policies demands tools able to measure the integration of refugees despite the complexity of such phenomena. In this work, we propose a set of metrics aimed at providing insights and assessing the integration of Syrians refugees, by analyzing the CDR dataset of the challenge. Specifically, we aim at assessing the integration of refugees, by exploiting the similarity between refugees and locals in terms of calling behavior and mobility, considering different spatial and temporal features. Together with the already known methods for data analysis, in this work we use a novel computational approach to analyze users' mobility: computational stigmergy, a bio-inspired scalar and temporal aggregation of samples. Computational stigmergy associates each sample to a virtual pheromone deposit (mark) defined in a multidimensional space and characterized by evaporation over time. Marks in spatiotemporal proximity are aggregated into functional structures called trail. The stigmergic trail summarizes the spatiotemporal dynamics in data and allows to compute the stigmergic similarity between them.I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
