在线社会网络中考虑用户体验的谣言阻断策略  

Rumor blocking strategies considering user experience in online social network

作　　者：丁学君[1] 李梦雨 Ding Xuejun;Li Mengyu(School of Management Science and Engineering,Dongbei University of Finance and Economics,Dalian 116025,China)

机构地区：[1]东北财经大学管理科学与工程学院,辽宁大连116025

出　　处：《系统工程学报》2020年第6期721-735,共15页Journal of Systems Engineering

基　　金：国家自然科学基金资助项目(71874025,71503033,71571033,71601038);辽宁省教育厅资助项目(LF201783608,LN2017FW004).

摘　　要：针对在线社会网络中的谣言控制问题,构建了一个考虑谣言整体流行度和个体传播倾向的动态谣言传播模型,基于此设计了一个考虑用户体验的谣言阻断算法.算法以基于双曲折扣效应的用户体验模型作为约束,利用贪心算法选取目标节点子集并加以阻断,以最大程度地减少在线社会网络中谣言扩散范围.实验结果表明,提出的动态阻断算法具有更好的阻断性能,且谣言阻断时间越早,阻断节点比例越大,谣言扩散范围越小;而当阻断节点比例较大时,需选取适当的阻断持续时间,以保证用户体验,避免舆情进一步演化.To control the spread of rumors in online social network,this paper builds a dynamic rumor spread model considering the overall popularity and individual tendency of rumors,and presents a rumor blocking algorithm considering user experiences.The algorithm introduces a hyperbolic discount effect-based user experience model as the constraint,and then designs a greedy algorithm to select the target node subset to block,which can minimize the spread of rumors in online social network.The results show that the dynamic blocking algorithm has better blocking performance;the earlier the start time of blocking is,or the larger the proportion of blocking nodes,the smaller the spreading range of rumor is.However,when the proportion of blocking nodes is large,appropriate blocking duration should be selected to ensure user experience and avoid further evolution of public opinion.

关 键 词：谣言阻断 在线社会网络 用户体验 贪心算法 

分 类 号：TP273[自动化与计算机技术—检测技术与自动化装置]