基于信息行为的社交网络节点信誉评估模型研究  

Reputation Evaluation Model in Social Network Based on Information Behavior

作　　者：熊建英[1] XIONG Jianying(Security Technology Department,Jiangxi Police Institute,Nanchang 330003,China)

机构地区：[1]江西警察学院科技与信息安全系,南昌330003

出　　处：《信息网络安全》2021年第12期51-59,共9页Netinfo Security

基　　金：江西省教育厅科技计划[GJJ212201]。

摘　　要：为促进社交网络用户自律与自治,提高社交网络的可信度,文章提出一种基于用户信息行为监督反馈的动态信誉评估方法。该方法在节点综合信誉评估中融合身份信誉与行为信誉机制,在动态更新中设置新节点考核期与分阶段信誉更新机制。通过节点信息披露、网络特征计算节点身份信誉;根据监督节点在社交网的信息发布、转发,对信息行为的自我纠正与不良信息阻断行为给与奖惩,形成行为信誉。实验结果表明,相比传统信任评估机制,对信息行为设置奖惩引导不仅可以提高信誉评估准确度,还可以抑制不良信息的交互。In order to promote self-discipline and autonomy of social network users and improve the credibility of social network, a dynamic reputation evaluation method based on user information behavior supervision and feedback is studied. The comprehensive reputation contains identity and behavior reputation, set evaluation period for a new node and update mechanism in different stage. Identity reputation is calculated by information disclosure and network characteristics;behavior reputation is calculated by information release and forwarding, and rewards or punishments will be given to self correction of information behavior or blocking of bad information. The simulation results show that compared with the traditional trust evaluation mechanism, setting rewards and punishments guidance can improve the accuracy of reputation evaluation. Reputation incentive can also inhibit the interaction of bad information.

关 键 词：社交网络 节点信誉 信息行为 信誉奖惩 网络治理 

分 类 号：TP309[自动化与计算机技术—计算机系统结构]