Examinando por Autor "Kaltenbrunner, Andreas"

Mostrando 1 - 1 de 1
  • Miniatura
    Publicación
    Computational Framework for the Assesment of New Forms of Political Organization in Social Media
    (Universidad Nacional de Educación a Distancia (España). Escuela Técnica Superior de Ingeniería Informática. Departamento de Inteligencia Artificial., 2016-07-07) Aragón Asenjo, Pablo; Kaltenbrunner, Andreas; Sarro Baro, Luis Manuel
    Social media has become a key mechanism for the organization of grassroots movements. In the 2015 Barcelona City Council election, Barcelona en Comú, an emerging grassroots party, was the most voted one. This candidacy was devised by activists involved in the Spanish 15M movement in order to turn citizen outrage into political change. On the one hand, the 15M movement is based on a decentralized structure. On the other hand, political science literature postulates that parties historically develop oligarchical leadership structures. This tension motivates to examine whether Barcelona en Comú preserved a decentralized structure or adopted a conventional centralized organization. This thesis proposes a computational framework to (1) better identify the Twitter networks of political parties by setting a confidence parameter in a popular community detection algorithm of the state of the art, and (2) analyze each party network by measuring the hierarchical structure, small-world phenomenon and coreness. The evaluation of the framework on the Twitter networks of the parties that ran for this election shows that the extended community detection algorithm effectively set boundaries between party networks. Although most parties consist of one single cluster, in Barcelona en Comú two well-defined groups co-exist: a cluster dominated by the party leader and the collective accounts, and another cluster formed by the movement activists. While the former group is highly centralized like traditional parties, the latter one stands out for its decentralized, cohesive and resilient structure.