A reliability-based approach for influence maximization using the evidence theory

Siwar Jendoubi (1, 2) , Arnaud Martin (2)

1 LARODEC - Laboratoire de Recherche Opérationnelle de Décision et de Contrôle de Processus
2 DRUID - Declarative & Reliable management of Uncertain, user-generated Interlinked Data

The influence maximization is the problem of finding a set of social network users, called influencers, that can trigger a large cascade of propagation. Influencers are very beneficial to make a marketing campaign goes viral through social networks for example. In this paper, we propose an influence measure that combines many influence indicators. Besides, we consider the reliability of each influence indicator and we present a distance-based process that allows to estimate the reliability of each indicator. The proposed measure is defined under the framework of the theory of belief functions. Furthermore, the reliability-based influence measure is used with an influence maximization model to select a set of users that are able to maximize the influence in the network. Finally, we present a set of experiments on a dataset collected from Twitter. These experiments show the performance of the proposed solution in detecting social influencers with good quality.

Mots clés: Influence measure; influence maximization; theory of belief functions; reliability; social network

Domaines: Intelligence artificielle [cs.AI]; Informatique [cs]

Siwar Jendoubi, Arnaud Martin. A reliability-based approach for influence maximization using the evidence theory. 19th International Conference on Big Data Analytics and Knowledge Discovery - DaWaK 2017, Aug 2017, Lyon, France. ⟨hal-01551780⟩