Fake reviews detection under belief function framework

Malika Ben Khalifa (1) , Zied Elouedi (1) , Eric Lefevre (2)

1 LARODEC - Laboratoire de Recherche Opérationnelle de Décision et de Contrôle de Processus
2 LGI2A - Laboratoire de Génie Informatique et d'Automatique de l'Artois

Online reviews have become one of the most important sources of customers opinions. These reviews influence potential purchasers to make or reverse decisions. Unfortunately, the existence of profit and publicity has emerged fake reviews to promote or demote some target products. Furthermore, reviews are generally imprecise and uncertain. So, it is a difficult task to uncover fake reviews from the genuine ones. In this paper, we propose a fake reviews detection method using the belief function theory. This method deals with the uncertainty in the given rating reviews and takes into account the similarity with other provided votes to detect misleading. We propose numerical examples to intuitively evaluate our method. Then, to prove its performance, we conducted on a real database. Experimentation shows that the proposed method is a valuable solution for the fake reviews detection problem.

Mots clés: Online opinions; Fake reviews; Uncertainty; Belief function theory

Domaines: Intelligence artificielle [cs.AI]

Malika Ben Khalifa, Zied Elouedi, Eric Lefevre. Fake reviews detection under belief function framework. International Conference on Advanced Intelligent Systems and Informatics, AISI'2018, Sep 2018, Caire, Egypt. pp.395-404, ⟨10.1007/978-3-319-99010-1_36⟩. ⟨hal-03643823⟩