Abstract The existing methods for predicting the popularity of online contents ignore the structural and temporal characteristics in the dynamic process of information cascades. To address this problem, a graph attention based spatial-temporal neural network(GAST-Net) is proposed to predict the popularity of online contents. The graph attention mechanism is adopted to learn the representation of cascade structure of online contents. Then, a temporal convolutional network is employed to capture the temporal features of information cascade. Finally, the popularity of online contents is mapped through a fully convolutional layer. Experimental results on datasets of Sina Weibo and American Physical Society demonstrate that GAST-Net model consistently outperforms the state-of-the-art methods.
Fund:Supported by National Natural Science Foundation of China(No.61702031), Beijing Excellent Talents Supporting Program(No.2017000020124G054), Fundamental Research Funds for the Central Universities(No. 2018JBM072), and CAS Key Laboratory of Network Data Science and Technology(No. CASNDST201702)
Corresponding Authors:
BAO Peng, Ph.D., associate professor. His research interests include data mining, social computing and machine learning.
About author:: XU Hao, master student. His research interests include data mining and machine lear-ning.
[1] BARABÁSI A L. The Origin of Bursts and Heavy Tails in Human Dynamics. Nature, 2005, 435: 207-211. [2] LESKOVEC J, ADAMIC L A, HUBERMAN B A. The Dynamics of Viral Marketing [J/OL]. [2019-07-15]. https://www.cs.cmu.edu/~jure/pubs/viral-tweb.pdf. [3] WATTS D J, DODDS P S. Influentials, Networks, and Public Opi-nion Formation. Journal of Consumer Research, 2007, 34(4): 441-458. [4] UGANDER J, BACKSTROM L, MARLOW C, et al. Structural Diversity in Social Contagion. Proceedings of the National Academy of Sciences of the United States of America, 2012, 109(16): 5962-5966. [5] PINTO H, ALMEIDA J M, GONCALVES M A. Using Early View Patterns to Predict the Popularity of Youtube Videos // Proc of the 6th ACM International Conference on Web Search and Data Mining. New York, USA: ACM, 2013: 365-374. [6] CHENG J, ADAMIC L A, DOW P A, et al. Can Cascades Be Predicted? // Proc of the 23rd International Conference on World Wide Web. New York, USA: ACM, 2014: 925-936. [7] ANDERSON A, HUTTENLOCHER D, KLEINBERG J, et al. Glo-bal Diffusion via Cascading Invitations: Structure, Growth, and Homophily // Proc of the 24th International Conference on World Wide Web. New York, USA: ACM, 2015: 66-76. [8] BAO P, SHEN H W, HUANG J M, et al. Popularity Prediction in Microblogging Network: A Case Study on Sina Weibo // Proc of the 22nd International Conference on World Wide Web. New York, USA: ACM, 2013: 177-178. [9] CRANE R, SORNETTE D. Robust Dynamic Classes Revealed by Measuring the Response Function of a Social System. Proceedings of the National Academy of Sciences of the United States of America, 2008, 105(41): 15649-15653. [10] MATSUBARA Y, SAKURAI Y, PRAKASH B A, et al. Rise and Fall Patterns of Information Diffusion: Model and Implications // Proc of the 18th ACM SIGKDD International Conference on Know-ledge Discovery and Data Mining. New York, USA: ACM, 2012: 6-14. [11] WANG D S, SONG C M, BARABÁSI A L. Quantifying Long-Term Scientific Impact. Science, 2013, 342(6154): 127-132. [12] SHEN H W, WANG D S, SONG C M, et al. Modeling and Predicting Popularity Dynamics via Reinforced Poisson Processes // Proc of the 28th AAAI Conference on Artificial Intelligence. Palo Alto, USA: AAAI Press, 2014: 291-297. [13] GAO S, MA J, CHEN Z M. Modeling and Predicting Retweeting Dynamics on Microblogging Platforms // Proc of the 8th ACM International Conference on Web Search and Data Mining. New York, USA: ACM, 2015: 107-116. [14] BAO P, SHEN H W, JIN X L, et al. Modeling and Predicting Popu-larity Dynamics of Microblogs Using Self-Excited Hawkes Processes // Proc of the 24th International Conference on World Wide Web. New York, USA: ACM, 2015: 9-10. [15] 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 Know-ledge Discovery and Data Mining. New York, USA: ACM, 2015: 1513-1522. [16] 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 Mana-gement. New York, USA: ACM, 2015: 1069-1078. [17] BAO P, ZHANG X X. Uncovering and Predicting the Dynamic Process of Collective Attention with Survival Theory. Scientific Reports, 2017, 7(1). DOI: 10.1007/s10115-016-0955-7. [18] LI C, MA J Q, GUO X X, et al. DeepCas: An End-to-End Predictor of Information Cascades // Proc of the 26th International Conference on World Wide Web. New York, USA: ACM, 2017: 577-586. [19] CAO Q, SHEN H W, CEN K T, et al. DeepHawkes: Bridging the Gap between Prediction and Understanding of Information Cascades // Proc of the 26th ACM International Conference on Information and Knowledge Management. New York, USA: ACM, 2017: 1149-1158. [20] VELICKOVIC P, CUCURULL G, CASANOVA A, et al. Graph Attention Network[C/OL]. [2019-07-15]. https://arxiv.org/ pdf/1710.10903.pdf. [21] BAI S, KOLTER J Z, KOLTUN V. An Empirical Evaluation of Generic Convolutional and Recurrent Networks for Sequence Mo-deling[C/OL]. [2019-07-15]. https://arxiv.org/pdf/1803.01271v1.pdf.
2019, Vol. 32 
