基于个体属性异质的微博信息超网络传播模型

A Weibo information hypernetwork propagation model based on individual attribute heterogeneity

摘要

异质网络能够有效建模现实世界的诸多复杂应用场景。基于微博平台个体的多样性，该文提出构建个体属性异质的微博信息超网络模型，模型以用户、话题为两类异质节点，用户参与话题讨论为超边，构建无标度异质超网络模型。在此基础上，结合SEIR传播模型，对异质节点的个体属性进行量化分析，通过元路径方法设计用户影响力、感染率和免疫率的计算方法。此外，通过仿真实验分析不同网络结构下信息传播的动态过程和规律，研究用户影响力、置信度、兴趣价值、信息时效性对该模型信息传播过程的影响。进一步，通过“日本核污水排放”事件验证模型的有效性和准确性。结果表明，该模型能够较为准确地描述真实社交网络中的信息传播趋势和过程。该工作对异质超网络的模型构建及超网络信息传播的研究有一定的借鉴意义，有助于深入研究更复杂多元的信息传播机制。

Abstract

Heterogeneous networks can effectively model various complex real-world application scenarios. Based on the diversity of individuals on the Weibo platform, this paper proposes a heterogeneous Weibo information hypernetwork model that incorporates individual attributes. In this model, users and topics are treated as two types of heterogeneous nodes, while user participation in topic discussions forms hyperedges, resulting in a scale-free heterogeneous hypernetwork model. Building on this framework, the SEIR propagation model is integrated to quantitatively analyze the individual attributes of heterogeneous nodes. Meta-path methods are employed to design calculation approaches for user influence, infection rate, and immunity rate. Furthermore, simulation experiments are conducted to analyze the dynamic processes and patterns of information dissemination across different network structures, investigating the impacts of user influence, confidence levels, interest values, and information timeliness on the dissemination process. Additionally, the validity and accuracy of the model are verified using the case study of the "Japan Nuclear Wastewater Discharge" incident. The results demonstrate that this model effectively captures the trends and processes of information dissemination in real social networks. This work provides valuable insights for research on the model construction of heterogeneous hypernetworks and hypernetwork-based information dissemination, contributing to a deeper understanding of more complex and diverse information propagation mechanisms.

关键词

超图 / 异质超网络 / 微博信息传播 / 个体属性异质 / 元路径

Key words

hypergraph / heterogeneous hypernetwork / Weibo information dissemination / individual attribute heterogeneity / meta-path

参考文献

[1] 沈旺, 时倩如, 王俊尧, 等. 基于超图的在线社交网络信息传播模型研究[J]. 情报学报, 2023, 42(3): 354-364.

[2] SHEN W, SHI Q R, WANG J Y, et al. Information dissemination model used in online social networks based on hypergraphs[J]. Journal of the China Society for Scientific and Technical Information, 2023, 42(3): 354-364.

[3] LUO T Y, XU D, CAO Z D, et al. Modeling the coupling propagation of information, behavior, and disease in multilayer heterogeneous networks[J]. IEEE Transactions on Computational Social Systems, 2024, 11(3): 4058-4070. DOI: 10.1109/TCSS.2023.3306014

[4] 康泽, 王建波, 阳成, 等. 控制策略对流行病首达时间的影响研究[J]. 电子科技大学学报, 2024, 53(1): 119-128.

[5] KANG Z, WANG J B, YANG C, et al. Study on the influence of control strategy on the first arrival time of epidemics[J]. Journal of University of Electronic Science and Technology of China, 2024, 53(1): 119-128.

[6] YAN D C, XIE W X, ZHANG Y W. Heterogeneous information network-based interest composition with graph neural network for recommendation[J]. Applied Intelligence, 2022, 52(10): 11199-11213. DOI: 10.1007/s10489-021-03018-6

[7] MOSCATO V, SPERLÌ G. A survey about community detection over on-line social and heterogeneous information networks[J]. Knowledge-Based Systems, 2021, 224: 107112. DOI: 10.1016/j.knosys.2021.107112

[8] LI T T, ZENG Z M, SUN S Q, et al. Constructing a multi-layer heterogeneous networks model to explore the public opinion evolution pattern of key users in public health emergencies[J]. Journal of Information Science, 2023, DOI: 10.1177/01655515231169953.

[9] 李若晨, 肖人彬. 基于改进狼群算法优化LSTM网络的舆情演化预测[J]. 复杂系统与复杂性科学, 2024, 21(1): 1-11.

[10] LI R C, XIAO R B. Public opinion evolution prediction based on LSTM network optimized by an improved wolf pack algorithm[J]. Complex Systems and Complexity Science, 2024, 21(1): 1-11.

[11] KERMACK W O, MCKENDRICK A G. A contribution to the mathematical theory of epidemics[J]. Proceedings of the Royal Society of London Series A, Containing Papers of a Mathematical and Physical Character, 1927, 115(772): 700-721. DOI: 10.1098/rspa.1927.0118

[12] ANDERSON R M. The population dynamics of infectious diseases: theory and applications[M]. [S. l.]: Springer, 2013.

[13] ZHANG M L, QIN S M, ZHU X X. Information diffusion under public crisis in BA scale-free network based on SEIR model: Taking COVID-19 as an example[J]. Physica A: Statistical Mechanics and Its Applications, 2021, 571: 125848. DOI: 10.1016/j.physa.2021.125848

[14] HOSSEINI S, ZANDVAKILI A. Information dissemination modeling based on rumor propagation in online social networks with fuzzy logic[J]. Social Network Analysis and Mining, 2022, 12(1): 34. DOI: 10.1007/s13278-022-00859-y

[15] NAGURNEY A, DONG J E, ZHANG D. A supply chain network equilibrium model[J]. Transportation Research Part E: Logistics and Transportation Review, 2002, 38(5): 281-303. DOI: 10.1016/S1366-5545(01)00020-5

[16] ESTRADA E, RODRÍGUEZ-VELÁZQUEZ J A. Subgraph centrality and clustering in complex hyper-networks[J]. Physica A: Statistical Mechanics and Its Applications, 2006, 364: 581-594. DOI: 10.1016/j.physa.2005.12.002

[17] XIAO H B, HU F, LI P Y, et al. Information propagation in hypergraph-based social networks[J]. Entropy, 2024, 26(11): 957. DOI: 10.3390/e26110957

[18] GONG Y C, WANG M, LIANG W, et al. UHIR: An effective information dissemination model of online social hypernetworks based on user and information attributes[J]. Information Sciences, 2023, 644: 119284. DOI: 10.1016/j.ins.2023.119284

[19] WANG J, WANG Z P, YU P, et al. The SEIR dynamic evolutionary model with Markov chains in hyper networks[J]. Sustainability, 2022, 14(20): 13036. DOI: 10.3390/su142013036

[20] MOLAEI S, BABAEI S, SALEHI M, et al. Information spread and topic diffusion in heterogeneous information networks[J]. Scientific Reports, 2018, 8: 9549. DOI: 10.1038/s41598-018-27385-2

[21] YI Y X, ZHANG Z F, YANG L T, et al. Reemergence modeling of intelligent information diffusion in heterogeneous social networks: The dynamics perspective[J]. IEEE Transactions on Network Science and Engineering, 2021, 8(2): 828-840. DOI: 10.1109/TNSE.2020.2975112

[22] MOLAEI S, ZARE H, VEISI H. Deep learning approach on information diffusion in heterogeneous networks[J]. Knowledge-Based Systems, 2020, 189: 105153. DOI: 10.1016/j.knosys.2019.105153

[23] LI Z, ZHANG J, ZHENG G Z, et al. A generative hypergraph model for double heterogeneity[J]. Journal of Complex Networks, 2023, 12(1): cnad048. DOI: 10.1093/comnet/cnad048

[24] MOLTMAN G A W. Heterogeneous hypergraphs models for collaboration networks: A bridge between mathematics and business[D]. Enschede: University of Twente, 2023.

[25] BERGE C. Packing problems and hypergraph theory: A survey[J]. Annals of Discrete Mathematics, 1979, 4: 3-37.

[26] BAYTAS I M, XIAO C, WANG F, et al. Heterogeneous hyper-network embedding[C]// Proceedings of the IEEE International Conference on Data Mining. New York: IEEE, 2018: 875-880.

[27] ZHU Y, GUAN Z Y, TAN S L, et al. Heterogeneous hypergraph embedding for document recommendation[J]. Neurocomputing, 2016, 216: 150-162. DOI: 10.1016/j.neucom.2016.07.030

[28] FU X Y, ZHANG J N, MENG Z Q, et al. MAGNN: Metapath aggregated graph neural network for heterogeneous graph embedding[C]//Proceedings of the Proceedings of the Web Conference 2020. New York: ACM, 2020: 2331-2341.

[29] SHANNON C E, WEAVER W. The mathematical theory of communication[M]. Urbana: University of lllinois Press, 1949.

[30] HU F, ZHAO H X, MA X J. An evolving hypernetwork model and its properties[J]. Scientia Sinica Physica, Mechanica & Astronomica, 2013, 43(1): 16.

[31] GENG L X, YANG S R, WANG K, et al. Modeling public opinion dissemination in a multilayer network with SEIR model based on real social networks[J]. Engineering Applications of Artificial Intelligence, 2023, 125: 106719. DOI: 10.1016/j.engappai.2023.106719

[32] WANG C X, WANG G S, LUO X P, et al. Modeling rumor propagation and mitigation across multiple social networks[J]. Physica A: Statistical Mechanics and Its Applications, 2019, 535: 122240. DOI: 10.1016/j.physa.2019.122240

[33] LI L F, ZHANG Q P, WANG X, et al. Characterizing the propagation of situational information in social media during COVID-19 epidemic: A case study on weibo[J]. IEEE Transactions on Computational Social Systems, 2020, 7(2): 556-562. DOI: 10.1109/TCSS.2020.2980007

基金资助

国家自然科学基金(62566052)

青海省自然科学基金(2023-ZJ-916M)