A Trust Algorithm based on the Latent Trust from Users to Items

DOI

10.2991/iccsae-15.2016.156How to use a DOI?

Keywords

trust algorithm; referral trust; latent trust; customer-to-customer trust; customer-to-commodity trust; trust network.

Abstract

Trust relationship plays an important role in helping customers arrive at a trade decision in e-commerce. Numerous models and prediction algorithms have been proposed to calculate trust value. However, these models and algorithms are impractical in e-commerce transaction. In this paper, customer-to-customer and customer-to-commodity trust relationship sub-networks are proposed to get clear trust network which can be maintained easily. Trust relationships are divided into three types which are functional trust, referral trust and latent trust. We propose a trust algorithm to compute the trust value of customer-to-commodity trust which can help customers to make final purchase decisions directly. Our algorithm is based on more comprehensive trust features such as the referral trust, latent trust, domain similarity of Web commodities that users are interested in, and the influence of different reputations of users within two sub-networks. Experiment results with data sets from Epinions.com illustrate more accurate trust prediction compared with those existed algorithms.

Copyright

© 2016, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - CONF
AU  - Meiyu Fang
AU  - Zhongkai Hu
PY  - 2016/02
DA  - 2016/02
TI  - A Trust Algorithm based on the Latent Trust from Users to Items
BT  - Proceedings of the 2015 5th International Conference on Computer Sciences and Automation Engineering
PB  - Atlantis Press
SP  - 834
EP  - 846
SN  - 2352-538X
UR  - https://doi.org/10.2991/iccsae-15.2016.156
DO  - 10.2991/iccsae-15.2016.156
ID  - Fang2016/02
ER  -