基于节点态度的社交网络信息传播模型
|
摘要
为了揭示信息在社交网络中传播的内在规律,对社交网络的信息传播过程进行深入的研究,社交网络的信息传播过程除了受信息本身的吸引力和社交环境的影响,同时受节点对消息的态度的影响。然而,现有信息传播模型对节点态度考虑不足,不能体现节点态度的差异对信息传播所产生影响。本文结合传染病模型并考虑节点态度,提出了一种基于节点态度的社交网络信息传播模型,旨在分析节点态度对信息传播的影响,为研究社交网络的信息传播机理提供理论依据。首先,考虑到不同节点的态度及其变化规则的差异,从个体角度出发,基于节点行为定义了节点态度及其更新原则。其次,在传统传染病动力学SIRS模型基础上,结合信息传播与传染病感染扩散类似的传播机理,综合考虑节点态度对信息传播状态转移的影响,利用社会学习理论得到一种基于节点态度的社交网络传播模型。该模型能够分析节点态度对信息传播的影响,给出传播规则,并刻画信息传播的演化规律。最后,采用新浪微博的真实数据对本文的传播模型进行了仿真实验,仿真结果验证了节点态度影响着信息的传播,证明了本文所提模型能够更准确地描述信息传播规律,反映社交网络的信息传播过程。
In order to reveal the inherent laws of information diffusion in social network,the process of information diffusion in social network was studied in-depth.It was found that the process of information diffusion in social network was not only influenced by the attraction of information and social environment,but also influenced by the attitude of nodes to information.However,the existing information diffusion models rarely considered the attitude of the nodes,and thuscould not reflect the impact of different attitudes of the nodes on the process of information diffusion.Therefore,a node attitude-based information diffusion model was proposed in social network,which combined the node attitude and SIRS model to analyze the influence of node attitude on information diffusion.It also provided the theoretical basis for the study of information diffusion mechanism in social network.In particular,considering the differences in the attitude of different nodes and their change rules,the node attitudes of nodes and their updating principles were respectively defined based on the node behavior.Furthermore,combining the information diffusion and the SIRS model-based infection spread mechanism as well as the impact of node attitude on diffusion state transition,an information diffusion model in social network based on node attitude were obtained by exploiting the social learning theory.The model could describe the diffusion rules,reveal the evolution law of information diffusion and analyze the influence of node attitude on information diffusion.At last,datasets from Sina micro-blog were used as the experimental data in the simulation.The simulation results showed that the attitude of node affected the information diffusion.Meanwhile,it was also demonstrated that the proposed model was more accurate in revealing the information diffusion law and reflecting the process of information diffusion.
In order to reveal the inherent laws of information diffusion in social network,the process of information diffusion in social network was studied in-depth.It was found that the process of information diffusion in social network was not only influenced by the attraction of information and social environment,but also influenced by the attitude of nodes to information.However,the existing information diffusion models rarely considered the attitude of the nodes,and thuscould not reflect the impact of different attitudes of the nodes on the process of information diffusion.Therefore,a node attitude-based information diffusion model was proposed in social network,which combined the node attitude and SIRS model to analyze the influence of node attitude on information diffusion.It also provided the theoretical basis for the study of information diffusion mechanism in social network.In particular,considering the differences in the attitude of different nodes and their change rules,the node attitudes of nodes and their updating principles were respectively defined based on the node behavior.Furthermore,combining the information diffusion and the SIRS model-based infection spread mechanism as well as the impact of node attitude on diffusion state transition,an information diffusion model in social network based on node attitude were obtained by exploiting the social learning theory.The model could describe the diffusion rules,reveal the evolution law of information diffusion and analyze the influence of node attitude on information diffusion.At last,datasets from Sina micro-blog were used as the experimental data in the simulation.The simulation results showed that the attitude of node affected the information diffusion.Meanwhile,it was also demonstrated that the proposed model was more accurate in revealing the information diffusion law and reflecting the process of information diffusion.
引文
[1]Hu Changjun,Xu Wenwen,Hu Ying,et al.Review of information diffusion in online social networks[J].Journal of Electronics&Information Technology,2017,39(4):794-804.[胡长军,许文文,胡颖,等.在线社交网络信息传播研究综述[J].电子与信息学报,2017,39(4):794-804.]
[2]Wu Dapeng,Yan Junjie,Wang Honggang,et al.Social attribute aware incentive mechanisms for video distribution in device-to-device communications[J].IEEE Transaction on Multimedia,2017,19(8):1908-1920.
[3]Wu Dapeng,Si Shushan,Wu Shaoen,et al.Dynamic trust relationships aware data privacy protection in mobile crowdsensing[J].IEEE Internet of Things Journal,2017,PP(99):1.
[4]Sun Guozi,Qiu Chengyan,Li Huakang.Micro-blog influence quantification model based on linear weight[J].Journal of Sichuan University(Engineering Science Edition),2016,48(1):78-84.[孙国梓,仇呈燕,李华康.基于线性加权的微博影响力量化模型[J].四川大学学报(工程科学版),2016,48(1):78-84.]
[5]Zhang Wei,Ye Yanqing,Tan Hanlin,et al.Information diffusion model based on social network[C]//Proceedings of the2012 International Conference of Modern Computer Science and Applications.Berlin:Springer,2013:145-150.
[6]Xia Chengyi,Sun Shiwei,Rao Feng,et al.SIS model of epidemic spreading on dynamical networks with community[J].Frontiers of Computer Science in China,2009,3(3):361-365.
[7]Zhang Yanchao,Liu Yun,Zhang Haifeng,et al.The researchof information dissemination model on online social network[J].Acta Physica Sinica,2011,60(5):60-66.[张彦超,刘云,张海峰,等.基于在线社交网络的信息传播模型[J].物理学报,2011,60(5):60-66.]
[8]Zheng Muhua,LüLinyuan,Zhao Ming.Spreading in online social networks:The role of social reinforcement[J].Physical Review E,Statistical,Nonlinear,and Soft Matter Physics,2013,88(1):2252-2279.
[9]Wang Chao,Yang Xuying,Xu Ke,et al.SEIR-based model for the information spreading over SNS[J].Chinese Journal of Electronics,2014,42(11):2325-2330.[王超,杨旭颖,徐珂,等.基于SEIR的社交网络信息传播模型[J].电子学报,2014,42(11):2325-2330.]
[10]Wang Jinlong,Liu Fangai,Zhu Zhenfang.An information spreading model based on relative weight in social network[J].Acta Physica Sinica,2015,64(5):63-73.[王金龙,刘方爱,朱振方.一种基于用户相对权重的在线社交网络信息传播模型[J].物理学报,2015,64(5):63-73.]
[11]Xu Jie,Yu Yahong,Gao Chengyi,et al.Nonlinear analysis and optimal control of an improved SIR rumor spreading model[J].Journal of Communications,2015,10(8):638-646.
[12]Meng Zaiqiao,Fu Xiufen.Dynamic information spreading model based on online social network[J].Journal of Computer Applications,2014,34(7):1960-1963.[蒙在桥,傅秀芬.基于在线社交网络的动态消息传播模型[J].计算机应用,2014,34(7):1960-1963.]
[13]Zhang Yaming,Tang Chaosheng,Li Weigang.Research on interest attenuation and social reinforcement mechanism for rumor spreading in online social networks[J].Journal of the China Society for Scientific and Technical Information,2015,34(8):833-844.[张亚明,唐朝生,李伟钢.在线社交网络谣言传播兴趣衰减与社会强化机制研究[J].情报学报,2015,34(8):833-844.]
[14]Zan Yongli,Wu Jianliang,Li Ping,et al.SICR rumor spreading model in complex networks:Counterattack and self-resistance[J].Physica A:Statistical Mechanics and Its Applications,2014,405:159-170.
[15]Liu Qipeng,Wang Xiaofan.Social learning with bounded confidence and heterogeneous agents[J].Physica A:Statistical Mechanics and Its Applications,2013,392(10):2368-2374.
[16]Karataev E,Zadorozhny V.Adaptive social learning based on crowdsourcing[J].IEEE Transactions on Learning Technologies,2017,10(2):128-139.
[2]Wu Dapeng,Yan Junjie,Wang Honggang,et al.Social attribute aware incentive mechanisms for video distribution in device-to-device communications[J].IEEE Transaction on Multimedia,2017,19(8):1908-1920.
[3]Wu Dapeng,Si Shushan,Wu Shaoen,et al.Dynamic trust relationships aware data privacy protection in mobile crowdsensing[J].IEEE Internet of Things Journal,2017,PP(99):1.
[4]Sun Guozi,Qiu Chengyan,Li Huakang.Micro-blog influence quantification model based on linear weight[J].Journal of Sichuan University(Engineering Science Edition),2016,48(1):78-84.[孙国梓,仇呈燕,李华康.基于线性加权的微博影响力量化模型[J].四川大学学报(工程科学版),2016,48(1):78-84.]
[5]Zhang Wei,Ye Yanqing,Tan Hanlin,et al.Information diffusion model based on social network[C]//Proceedings of the2012 International Conference of Modern Computer Science and Applications.Berlin:Springer,2013:145-150.
[6]Xia Chengyi,Sun Shiwei,Rao Feng,et al.SIS model of epidemic spreading on dynamical networks with community[J].Frontiers of Computer Science in China,2009,3(3):361-365.
[7]Zhang Yanchao,Liu Yun,Zhang Haifeng,et al.The researchof information dissemination model on online social network[J].Acta Physica Sinica,2011,60(5):60-66.[张彦超,刘云,张海峰,等.基于在线社交网络的信息传播模型[J].物理学报,2011,60(5):60-66.]
[8]Zheng Muhua,LüLinyuan,Zhao Ming.Spreading in online social networks:The role of social reinforcement[J].Physical Review E,Statistical,Nonlinear,and Soft Matter Physics,2013,88(1):2252-2279.
[9]Wang Chao,Yang Xuying,Xu Ke,et al.SEIR-based model for the information spreading over SNS[J].Chinese Journal of Electronics,2014,42(11):2325-2330.[王超,杨旭颖,徐珂,等.基于SEIR的社交网络信息传播模型[J].电子学报,2014,42(11):2325-2330.]
[10]Wang Jinlong,Liu Fangai,Zhu Zhenfang.An information spreading model based on relative weight in social network[J].Acta Physica Sinica,2015,64(5):63-73.[王金龙,刘方爱,朱振方.一种基于用户相对权重的在线社交网络信息传播模型[J].物理学报,2015,64(5):63-73.]
[11]Xu Jie,Yu Yahong,Gao Chengyi,et al.Nonlinear analysis and optimal control of an improved SIR rumor spreading model[J].Journal of Communications,2015,10(8):638-646.
[12]Meng Zaiqiao,Fu Xiufen.Dynamic information spreading model based on online social network[J].Journal of Computer Applications,2014,34(7):1960-1963.[蒙在桥,傅秀芬.基于在线社交网络的动态消息传播模型[J].计算机应用,2014,34(7):1960-1963.]
[13]Zhang Yaming,Tang Chaosheng,Li Weigang.Research on interest attenuation and social reinforcement mechanism for rumor spreading in online social networks[J].Journal of the China Society for Scientific and Technical Information,2015,34(8):833-844.[张亚明,唐朝生,李伟钢.在线社交网络谣言传播兴趣衰减与社会强化机制研究[J].情报学报,2015,34(8):833-844.]
[14]Zan Yongli,Wu Jianliang,Li Ping,et al.SICR rumor spreading model in complex networks:Counterattack and self-resistance[J].Physica A:Statistical Mechanics and Its Applications,2014,405:159-170.
[15]Liu Qipeng,Wang Xiaofan.Social learning with bounded confidence and heterogeneous agents[J].Physica A:Statistical Mechanics and Its Applications,2013,392(10):2368-2374.
[16]Karataev E,Zadorozhny V.Adaptive social learning based on crowdsourcing[J].IEEE Transactions on Learning Technologies,2017,10(2):128-139.