Centrality measures to identify leaders in criminal networks

Guest Lecture Series

2 April 2019
Versione stampabile

Location: School of International Studies, Palazzo Paolo Prodi, via T. Gar 14 Trento, Room 001
Time: from 14:15 to 16:00

Guest Speaker

  • Rosanna Grassi - University of Milano-Bicocca

Abstract

Centrality measures are introduced as importance  measures  to  quantify the  role  or position of a  node in a network.
In analysing communications among criminals, which naturally induce bipartite networks, studies have focused on the classic Freeman's betweenness centrality, conceived for one-mode matrices and possibly biasing the results. We explore different betweenness centrality including three inspired by the so-called “dual projection approach” . We test these measures in identifying criminal leaders in a meeting participation network. Despite the expected high correlations among them, the measures yield different node rankings, capturing different characteristics of brokerage. Overall, the dual projection approaches show higher success than classic approaches in identifying the criminal leaders.