An unsupervised Bayesian neural network for truth discovery in social networks

• Main Authors: Yang, Jielong, Tay, Wee Peng
• Other Authors: School of Electrical and Electronic Engineering
• Format: Article
• Language: English
• Published: 2021
• Subjects: Engineering::Electrical and electronic engineering; Truth Discovery; Unsupervised Learning
• Online Access: https://hdl.handle.net/10356/153704
• Institution: Nanyang Technological University

The problem of estimating event truths from conflicting agent opinions in a social network is investigated. An autoencoder learns the complex relationships between event truths, agent reliabilities and agent observations. A Bayesian network model is proposed to guide the learning process by modeling...