Predict Pairwise Trust based on Machine Learning in Online Social Networks: A Survey

Loading...
Thumbnail Image

Access rights

openAccess
publishedVersion

URL

Journal Title

Journal ISSN

Volume Title

A2 Katsausartikkeli tieteellisessä aikakauslehdessä

Major/Subject

Mcode

Degree programme

Language

en

Pages

Series

IEEE Access, Volume 6, pp. 51297-51318

Abstract

Trust plays a crucial role in online social networks where users do not communicate or interact with each other in a direct face-to-face manner. Although many researchers have already conducted comprehensive studies on trust computing like trust evaluation, pairwise trust prediction is still relatively under explored especially with machine learning methods which can overcome the disadvantages of both linear predication and trust propagation. This survey aims to fill this gap and first provides an overview of state-of-the-art researches in pairwise trust prediction using machine learning techniques, especially in the context of social networking. Specifically, we present a workflow of trust prediction using machine learning and summarize current available trust-related datasets, classifiers and different metrics used to evaluate a trained classifier. Also, we review, compare, and contrast the literature for the purpose of identifying open issues and directing future research.

Description

Other note

Citation

Liu, S, Zhang, L & Yan, Z 2018, 'Predict Pairwise Trust based on Machine Learning in Online Social Networks : A Survey', IEEE Access, vol. 6, pp. 51297-51318. https://doi.org/10.1109/ACCESS.2018.2869699