An Adaptive Distributed Consumer Trust Model for Social Commerce

Abstract

Consumer trust is a crucial issue in social commerce, i.e. how to help consumers find trustworthy products. However, the current evaluation system in the market has significant shortcomings. This can be improved by trust and reputation modeling, but the existing models have flaws. This paper proposes an adaptive distributed trust model. The main features of its algorithm include (1) When calculating product trustworthiness, evaluations from consumers themselves, social networks, and e-commerce platforms are integrated, and the importance of these three sources of trust can change adaptively as consumers learn. (2) When selecting product providers and advisers, the Softmax algorithm is used to deal with the “exploration or exploitation” dilemma in reinforcement learning. (3) Consider the emotional attachment between consumers and advisers. (4) Design a blacklist mechanism to determine alternative product providers. The main contribution of this study lies in this model. Comparison with existing typical models shows that in various market scenarios, or when different market features change, this model can provide consumers with higher utility. This is because it better fits the characteristics of social commerce and has stronger adaptability. The results of this paper can not only provide a foundational model for related research but also can be used to develop a novel distributed product evaluation system for social commerce.