1. College of Computer and Data Science, Fuzhou University, Fuzhou 350108 2. Fujian Provincial Key Laboratory of Networking Computing and Intelligent Information Processing, Fuzhou University, Fuzhou 350108 3. Digital Fujian Institute of Financial Big Data, Fuzhou University, Fuzhou 350108 4. College of Electronics and Information Science, Fujian Jiangxa University, Fuzhou 350108 5. Research Center for Cyberspace Security, Peng Cheng Laboratory, Shenzhen 518000
Abstract The existing information diffusion prediction methods model the cascade sequences and topological structure independently. And thus it is difficult to learn the interactive expression of cascade temporal and structural features in the embedded space, and the portrayal of dynamic evolution of information diffusion is insufficient. Aiming at this problem, an information diffusion prediction method based on cascade spatial-temporal feature is proposed. Based on the social network and diffusion paths, the heterogeneous graphs are constructed. The structural context of nodes of heterogeneous graphs and social network is learned by graph neural network, while the cascade temporal feature is captured by gated recurrent unit. To make microscopic information prediction, the cascade spatial-temporal feature is constructed by fusing structure context and temporal feature. The experimental results on Twitter and Memes datasets demonstrate that the performance of the proposed method is improved to a certain extent.
Fund:National Natural Science Foundation of China(No.61976054)
Corresponding Authors:
LIAO Xiangwen, Ph. D., professor. His research interests include opinion mining, sentiment analysis and natural language processing.
About author:: LIANG Shaobin, master student. His research interests include online social network analysis and natural language processing. CHEN Zhihao, Ph.D. candidate. His research interests include social network information diffusion analysis and sentiment analysis. WU Yunbing, master, associate professor. His research interests include machine lear-ning, data mining and knowledge representation.
[1] 廖祥文,郑候东,刘盛华,等.基于用户行为的情感影响力和易感性学习.计算机学报, 2017, 40(4): 955-969. (LIAO X W, ZHENG H D, LIU S H, et al. Learning Influences and Susceptibilities for Sentiments from Users' Behaviors. Chinese Journal of Computers, 2017, 40(4): 955-969.) [2] YANG Y, TANG J, LEUNG C W, et al. Rain: Social Role-Aware Information Diffusion // Proc of the 29th AAAI Conference on Artificial Intelligence. Palo Alto, USA: AAAI Press, 2015: 367-373. [3] WOO J, CHEN H. An Event-Driven Sir Model for Topic Diffusion in Web Forums // Proc of the IEEE International Conference on Intelligence and Security Informatics. Washington, USA: IEEE, 2012: 108-113. [4] WOO J, SON J, CHEN H. An Sir Model for Violent Topic Diffusion in Social Media // Proc of the IEEE International Conference on Intelligence and Security Informatics. Washington, USA: IEEE, 2011: 15-19. [5] MISHRA S, RIZOIU M A, XIE L X. Feature Driven and Point Process Approaches for Popularity Prediction // Proc of the 25th ACM International Conference on Information and Knowledge Ma-nagement. New York, USA: ACM, 2016: 1069-1078. [6] ZHAO Q Y, ERDOGDU M A, HE H Y, et al. SEISMIC: A Self-Exciting Point Process Model for Predicting Tweet Popularity // Proc of the 21st ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. New York, USA: ACM, 2015: 1513-1522. [7] WANG Y Q, SHEN H W, LIU S H, et al. Cascade Dynamics Mo-deling with Attention-Based Recurrent Neural Network // Proc of the 26th International Joint Conference on Artificial Intelligence. New York, USA: ACM, 2017: 2985-2991. [8] LI C, MA J Q, GUO X X, et al. Deepcas: An End-to-End Predictor of Information Cascades // Proc of the 26th International Confe-rence on World Wide Web. New York, USA: ACM, 2017: 577-586. [9] CAO Q, SHEN H W, CEN K T, et al. DeepHawkes: Bridging the Gap between Prediction and Understanding of Information Cascades // Proc of the ACM Conference on Information and Knowledge Ma-nagement. New York, USA: ACM, 2017: 1149-1158. [10] WANG Z T, LI W J. Hierarchical Diffusion Attention Network // Proc of the 28th International Joint Conference on Artificial Intelligence. New York, USA: ACM, 2019: 3828-3834. [11] CHEN X Q, ZHOU F, ZHANG K P, et al. Information Diffusion Prediction via Recurrent Cascades Convolution // Proc of the 35th IEEE International Conference on Data Engineering. Washington, USA: IEEE, 2019: 770-781. [12] CAO Q, SHEN H W, GAO J H, et al. Popularity Prediction on Social Platforms with Coupled Graph Neural Networks // Proc of the 13th International Conference on Web Search and Data Mining. New York, USA: ACM, 2020: 70-78. [13] WANG J, ZHENG V W, LIU Z M, et al. Topological Recurrent Neural Network for Diffusion Prediction // Proc of the IEEE International Conference on Data Mining. Washington, USA: IEEE, 2017: 475-484. [14] WANG Z T, CHEN C Y, LI W J. A Sequential Neural Information Diffusion Model with Structure Attention // Proc of the 27th ACM International Conference on Information and Knowledge Management. New York, USA: ACM, 2018: 1795-1798. [15] YUAN C Y, LI J C, ZHOU W, et al. DyHGCN: A Dynamic He-terogeneous Graph Convolutional Network to Learn Users' Dynamic Preferences for Information Diffusion Prediction // Proc of the Joint European Conference on Machine Learning and Knowledge Disco-very in Databases. Berlin, Germany: Springer, 2020: 347-363. [16] YANG C, TANG J, SUN M S, et al. Multi-scale Information Di-ffusion Prediction with Reinforced Recurrent Networks // Proc of the 28th International Joint Conference on Artificial Intelligence. New York, USA: ACM, 2019: 4033-4039. [17] CHEN X, ZHANG K P, ZHOU F, et al. Information Cascades Modeling via Deep Multi-task Learning // Proc of the 42nd International ACM SIGIR Conference on Research and Development in Information Retrieval. New York, USA: ACM, 2019: 885-888. [18] CUI B R, YANG S J, HOMAN C. Non-independent Cascade Formation: Temporal and Spatial Effects // Proc of the 23rd ACM International Conference on Information and Knowledge Management. New York, USA: ACM, 2014: 1923-1926. [19] HODAS N O, LERMAN K. The Simple Rules of Social Contagion. Scientific Reports, 2014, 4(1). DOI: 10.1038/srep04343. [20] LESKOVEC J, BACKSTROM L, KLEINBERG J. Meme-Tracking and the Dynamics of the News Cycle // Proc of the 15th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. New York, USA: ACM, 2009: 497-506. [21] ISLAM M R, MUTHIAH S, ADHIKARI B, et al. DeepDiffuse: Predicting the 'Who' and 'When' in Cascades // Proc of the IEEE International Conference on Data Mining. Washington, USA: IEEE, 2018: 1055-1060.
2021, Vol. 34 
