Dynamic Trust Models between Users over Social Networks
Abstract
In this project, by focusing on a number of word-of-mouth communication websites, we attempted to construct dynamic trust models between users that enable to explain trust formation and its evolution processes over social networks with reasonable accuracy. Consequently, we obtained our research results on four new approaches, 1) to rank items based on the MTDF (Multinomial with Trust Discount Factor) model, 2) to estimate the conformity of users from the observed review scores, 3) to predict evolution of trust links under the presence of mediators, and 4) to analyze activities among users based on a non-negative matrix factorization (NMF) method. By using the datasets of item review scores and trust networks collected from a number of websites such as Epinions, we confirmed that our proposed models and methods can be useful basic techniques for uncovering fundamental mechanisms of trust formation and its evolution processes over trust networks. During our research period, we presented 3 papers published in peer-reviewed journals and 13 papers published in peer-reviewed conference proceedings as attached in this report.
Document Details
- Document Type
- Technical Report
- Publication Date
- Mar 30, 2016
- Accession Number
- ADA636879
Entities
People
- Kazumi SaitÅ
Organizations
- University of Shizuoka