Wen Dong

Virtual Networks and Poverty Analysis in Senegal

Virtual network for Senegal at region level with MPI (Multi-dimensional Poverty Index) as an overlay. Thickness of links indicates the volume of calls and texts exchanged between a pair of regions. Size of the circle at each region indicates the total number of Mourning and outgoing calls and texts for the region. Note that regions with plenty of strong links have lower poverty, while most poor regions appear isolated.

Virtual network for Senegal at region level with MPI (Multi-dimensional Poverty Index) as an overlay. Thickness of links indicates the volume of calls and texts exchanged between a pair of regions. Size of the circle at each region indicates the total number of Mourning and outgoing calls and texts for the region. Note that regions with plenty of strong links have lower poverty, while most poor regions appear isolated.

Neeti Pokhriyal and Wen Dong

Computer Science and Engineering

State University of New York at Buffalo

Can the accessibility of mobile technology be used to identify, characterize and alleviate poverty? This project is an attempt to answer this question. We conduct two studies.

1. Using the cellular-communications data, we construct virtual connectivity maps for Senegal. The spatial regions are nodes and the cellular communications between regions are links. The connectivity is then correlated with the poverty indicators. Our model predicts poverty index and generates a poverty map for Senegal at an unprecedented fine resolution.

2. We study how phone usage behavior, gathered from cellular-communications, correlates with the poverty indicators. Using only this relationship can also give us a poverty map. Since poverty is a complex phenomenon, poverty maps showcasing multiple perspectives, such as ours, provide policymakers with better insights for effective responses for poverty eradication.