Análise de redes sociais em criminologia com a composição probabilística de preferências

Abstract

Several researches have applied social network analysis to reveal the dynamics of criminal organizations, particularly the identification of critical actors in the networks, who can be directed by law enforcement officials for a more detailed investigation and subsequent disruption. In this article, the Caviar Project, an antidrug operation by the Canadian police, together with other countries (including Brazil), was reassessed in the light of different measures of centrality, using a multicriteria decision aid method. The article brings a novel approach to the Composition of Probabilistic Preferences for sorting problems (CPP TRI). Scenarios were established with class profiles with increasing restriction, in order to progressively select the number of upperclass actors. Therefore, only actors with better performance are kept in the upper class. The results would have been useful to the Caviar agents, as they indicated actors with high degrees of centrality that were not prioritized in the investigations.