The Advantage of Evidential Attributes in Social Networks

Salma Ben Dhaou (1, 2) , Kuang Zhou (3) , Mouloud Kharoune (2) , Arnaud Martin (2) , Boutheina Ben Yaghlane (1)

1 LARODEC - Laboratoire de Recherche Opérationnelle de Décision et de Contrôle de Processus
2 DRUID - Declarative & Reliable management of Uncertain, user-generated Interlinked Data
3 NPU - Northwestern Polytechnical University [Xi'an]

Nowadays, there are many approaches designed for the task of detecting communities in social networks. Among them, some methods only consider the topological graph structure, while others take use of both the graph structure and the node attributes. In real-world networks, there are many uncertain and noisy attributes in the graph. In this paper, we will present how we detect communities in graphs with uncertain attributes in the first step. The numerical, probabilistic as well as evidential attributes are generated according to the graph structure. In the second step, some noise will be added to the attributes. We perform experiments on graphs with different types of attributes and compare the detection results in terms of the Normalized Mutual Information (NMI) values. The experimental results show that the clustering with evidential attributes gives better results comparing to those with probabilistic and numerical attributes. This illustrates the advantages of evidential attributes.

Mots clés: Belief function theory; social networks; community detection

Domaines: Intelligence artificielle [cs.AI]; Réseaux sociaux et d'information [cs.SI]

Salma Ben Dhaou, Kuang Zhou, Mouloud Kharoune, Arnaud Martin, Boutheina Ben Yaghlane. The Advantage of Evidential Attributes in Social Networks. 20th International Conference on Information Fusion, Jul 2017, Xi'an, China. ⟨hal-01562965v2⟩