Implicit User Trust Modeling Based on User Attributes and Behavior in Online Social Networks

• Published in: IEEE access Vol. 7; pp. 142826 - 142842
• Main Authors: Khan, Jebran, Lee, Sungchang
• Format: Journal Article
• Language: English
• Published: Piscataway IEEE 2019; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Computational modeling; Credibility; Digital media; Estimation; Modelling; Psychology; Reliability; Social networking (online); Social networks; social-ties strength; Sociology; Systematics; Trust; trust-aware recommendation; Trustworthiness; User behavior; user trustworthiness modeling
• ISSN: 2169-3536; 2169-3536
• DOI: 10.1109/ACCESS.2019.2943877

In this paper, we present a new user trustworthiness estimation model for social networks (SN), whereas most of existing researches have been focused on the user-user/item relationship trustworthiness estimation. Users share information of their interest on various social media without their trustworthiness verification. Therefore, SN are susceptible to malicious users for misinformation spreading. In SN, the original information source is generally unknown and the user who is sharing the contents is the only known information about the source. Therefore, the user's trustworthiness is an effective criterion for SN content's trustworthiness estimation. However, the users are unable to identify trustworthy/untrustworthy users, and the existing user-user/item relationship models do not provide user trustworthiness information. Our proposed model provides a systematic way to assess the user trustworthiness based on user attributes and interaction behavior. The proposed model is helpful to avoid the trust sparsity (implicit trust model), trust subjectivity (user's objective/collective trustworthiness estimation model) and cold-start user's trustworthiness (user's attributes-based trust modeling) problems. We employ friends-recommendation (FR) as an exemplary application to evaluate the performance of our proposed model in trust-aware recommendations. Simulation results illustrate that our trust-aware FR model outperformed the existing trust and FR models.