Measuring and mitigating behavioural segregation using Call Detail Records


EPJ Data Science




D. Rhoads, A. Solé-Ribalta, J. Borge-Holthoefer, I. Serrano




The overwhelming amounts of data we generate in our daily routine and in social networks has been crucial for the understanding of various social and economic factors. The use of this data represents a low-cost alternative source of information in parallel to census data and surveys. Here, we advocate for such an approach to assess and alleviate the segregation of Syrian refugees in Turkey. Using a large dataset of mobile phone records provided by Turkey’s largest mobile phone service operator, Türk Telekom, in the frame of the Data 4 Refugees project, we define, analyse and optimise inter-group integration as it relates to the communication patterns of two segregated populations: refugees living in Turkey and the local Turkish population. Our main hypothesis is that making these two communities more similar (in our case, in terms of behaviour) may increase the level of positive exposure between them, due to the well-known sociological principle of homophily. To achieve this, working from the records of call and SMS origins and destinations between and among both populations, we develop an extensible, statistically-solid, and reliable framework to measure the differences between the communication patterns of two groups. In order to show the applicability of our framework, we assess how house mixing strategies, in combination with public and private investment, may help to overcome segregation. We first identify the districts of the Istanbul province where refugees and local population communication patterns differ in order to then utilise our framework to improve the situation. Our results show potential in this regard, as we observe a significant reduction of segregation while limiting, in turn, the consequences in terms of rent increase.