动态信任感知的偏好演化模型研究

Research on dynamic trust-aware preferences evolution model

有界置信模型(bounded confidence model,BCM)是舆论动力学中对偏好演化进行建模的重要模型,但其假设个体会完全接受与之交流个体的偏好以及所有的个体会诚实表达其偏好与实际情况不符,存在明显不足。针对该问题,提出了一种动态信任感知的偏好演化模型(dynamic trust-aware preferences evolution model,DTPEM)。首先,引入偏好接受度算子建模个体对交互对象偏好的接受度;其次,引入动态信任度算子度量个体偏好表达的诚实程度;然后建模偏好差距对信任度的影响。基于智能体模拟仿真实验与其他模型进行对比,结果表明,DTPEM在偏好演化的准确度上有了较大幅度的提升。

BCM is an important model used to model users’preferences evolution.But the model assumes that an agent will accept all agents’preference which interacting with it and express their preferences honestly.This assumption doesn’t accord with the reality and brings obvious deficiency.To solve this problem,this paper proposed a DTPEM.Firstly,DTPEM introduced an operator of acceptable degree of interactional preference,to describe the degrees of the agent’s acceptance to the interactional preferences of the interactional objects.Secondly,the model introduced an operator of dynamic trustable degree to describe the honest degrees of the expression of user preferences.Then,it modeled the influences of the preference differences to the dynamic trustable degrees.Compared with other existing mode,the experimental results demonstrate that the DTPEM has great increase in the accuracy of preference evolution.