01whole.pdf (2.21 MB)
Download file

Context-based social trust relationship prediction

Download (2.21 MB)
posted on 23.11.2022, 00:13 authored by Rongwei Xu

Social trust relationship prediction targets using attributes to quantify the interrelationships in trust between users, and this trust can be applied in both decision-making and product recommendation. Most of the existing algorithms do not consider the heterogeneity and the semantics of information included in online social networks, leading to low adaptability in capturing user preferences. What’s more, they only focus on directly connected nodes and treat all the information propagation paths equally, leading to the lack of structured context information. Given the incomplete graph structure on online social networks constructed by existing algorithms, they can hardly have good performance in the trust prediction.

To solve the above-mentioned problems, we propose a novel Context-based Social Trust Relation Prediction (CSTRP) model, which can capture different features on both nodes and paths adaptively based on the complex contexts and take multi-hop neighbours into account. Specifically, in our model, we construct a heterogeneous graph of three kinds of nodes: User, Interest, and Relationship, as well as two different meta-paths: User-Interest-User, and User-Relative-User. Then, we adopt a two-level attention mechanism to obtain the attention value on both the node-level and path-level. To incorporate the multi-hop neighbours’ information, we develop a 2-hop attention diffusion to aggregate the information from the indirectly connected nodes. The experimental results on real-world datasets have demonstrated that CSTRP outperforms the state-of-the-art methods in terms of the accuracy of social trust prediction.


Table of Contents

1 Introduction -- 2 Literature review -- 3 Methodology -- 4 Experiment and analysis -- 5 Conclusions and future research -- References


A thesis submitted to Macquarie University for the degree of Master of Research

Awarding Institution

Macquarie University

Degree Type

Thesis MRes


Thesis MRes, Macquarie University, School of Computing, 2022

Department, Centre or School

School of Computing

Year of Award


Principal Supervisor

Guanfeng Liu


Copyright: The Author Copyright disclaimer: https://www.mq.edu.au/copyright-disclaimer




74 pages