Publication Type

Conference Proceeding Article

Publication Date

4-2008

Abstract

A satisfactory and robust trust model is gaining importance in addressing information overload, and helping users collect reliable information in online communities. Current research on trust prediction strongly relies on a web of trust, which is directly collected from users based on previous experience. However, the web of trust is not always available in online communities and even though it is available, it is often too sparse to predict the trust value between two unacquainted people with high accuracy. In this paper, we propose a framework to derive degree of trust based on users' expertise and users' affinity for certain contexts (topics), using users rating data which is available and much more dense than direct trust data. In experiments with a real-world dataset, we show that our model can predict trust connectivity with a high degree of accuracy. With this framework, we can predict trust connectivity and degree of trust without a web of trust and then apply it to online community applications, e.g. e-commerce environments with users rating data.

Keywords

information overload, online community, robust Web trust model

Discipline

Databases and Information Systems | Numerical Analysis and Scientific Computing

Research Areas

Data Management and Analytics

Publication

IEEE 24th International Conference on Data Engineering Workshop: ICDEW 2008: Cancun, Mexico, 7-12 April 2008: Proceedings

First Page

531

Last Page

536

ISBN

9781424421626

Identifier

10.1109/ICDEW.2008.4498374

Publisher

IEEE

City or Country

Piscataway, NJ

Additional URL

http://dx.doi.org/10.1109/ICDEW.2008.4498374

Share

COinS