Quantifying trust dynamics in signed graphs, the S-Cores approach - LIRMM - Laboratoire d’Informatique, de Robotique et de Microélectronique de Montpellier Accéder directement au contenu
Communication Dans Un Congrès Année : 2014

Quantifying trust dynamics in signed graphs, the S-Cores approach

Résumé

Lately, there has been an increased interest in signed net-works with applications in trust, security, or social comput-ing. This paper focuses on the issue of defining models and metrics for reciprocity in signed graphs. In unsigned di-rected networks, reciprocity quantifies the predisposition of network members in creating mutual connections. On the other hand, this concept has not yet been investigated in the case of signed graphs. We capitalize on the graph degener-acy concept to identify subgraphs of the signed network in which reciprocity is more likely to occur. This enables us to assess reciprocity at a global level, rather than at an exclu-sively local one as in existing approaches. The large scale experiments we perform on real world data sets of trust net-works lead to both interesting and intuitive results. We be-lieve these reciprocity measures can be used in various social applications such as trust management, community detection and evaluation of individual nodes. The global reciprocity we define in this paper is closely correlated to the clustering structure of the graph, more than the local reciprocity as it is indicated by the experimental evaluation we conducted.
Fichier principal
Vignette du fichier
comrecipr.pdf (385.07 Ko) Télécharger le fichier
Origine : Publication financée par une institution
Loading...

Dates et versions

lirmm-01083529 , version 1 (17-11-2014)

Identifiants

Citer

Christos Giatsidis, Bogdan Cautis, Silviu Maniu, Michalis Vazirgiannis, Dimitrios M. Thilikos. Quantifying trust dynamics in signed graphs, the S-Cores approach. SDM 2014 - 14th SIAM International Conference on Data Mining, Aug 2014, Philadelphia, United States. pp.668-676, ⟨10.1137/1.9781611973440.77⟩. ⟨lirmm-01083529⟩
710 Consultations
485 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More