Abstract
This paper studies the Influence Maximization problem based on information cascading within a random graph, where the network structure is dynamically changing according to users’ uncertain behaviors. The Discrete Choice Model is used to define the probability distribution of the directed arcs between any two nodes in the random graph. The discrete choice model provides a good description and prediction of user behavior following/unfollowing their neighbor node. To find the maximal influence at the end of the finite time horizon, this paper proposed Multi-Stage Stochastic Programming models, which can help the decision maker to select the optimal seed nodes to broadcast messages efficiently. To approximate the optimal decisions, the paper discuss two approaches, i.e., the Myopic Two-Stage Stochastic Programming at each time period, and Reinforcement Learning for Markov Decision Process. Computational experiments show that the Reinforcement Learning method exhibits better performance than the Myopic method in large-scale networks.
This material is based on work supported by the AFRL Mathematical Modeling and Optimization Institute.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Chen, W., Wang, C., Wang, Y.: Scalable influence maximization for prevalent viral marketing in large-scale social networks. In: Proceedings of the 16th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 1029–1038. ACM (2010)
Kempe, D., Kleinberg, J., Tardos, É.: Maximizing the spread of influence through a social network. In: Proceedings of the Ninth ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 137–146. ACM (2003)
Oinas-Kukkonen, H.: A foundation for the study of behavior change support systems. Pers. Ubiquit. Comput. 17(6), 1223–1235 (2013)
Ploderer, B., Reitberger, W., Oinas-Kukkonen, H., Gemert-Pijnen, J.: Social interaction and reflection for behaviour change. Pers. Ubiquit. Comput. 18(7), 1667–1676 (2014)
Saito, K., Nakano, R., Kimura, M.: Prediction of information diffusion probabilities for independent cascade model. In: Lovrek, I., Howlett, R.J., Jain, L.C. (eds.) KES 2008. LNCS (LNAI), vol. 5179, pp. 67–75. Springer, Heidelberg (2008). https://doi.org/10.1007/978-3-540-85567-5_9
Wang, C., Chen, W., Wang, Y.: Scalable influence maximization for independent cascade model in large-scale social networks. Data Min. Knowl. Disc. 25(3), 545–576 (2012)
Yu, L., Cui, P., Wang, F., Song, C., Yang, S.: From micro to macro: uncovering and predicting information cascading process with behavioral dynamics. arXiv preprint arXiv:1505.07193 (2015)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2019 Springer Nature Switzerland AG
About this paper
Cite this paper
Chen, M., Zheng, Q.P., Boginski, V., Pasiliao, E.L. (2019). Reinforcement Learning in Information Cascades Based on Dynamic User Behavior. In: Tagarelli, A., Tong, H. (eds) Computational Data and Social Networks. CSoNet 2019. Lecture Notes in Computer Science(), vol 11917. Springer, Cham. https://doi.org/10.1007/978-3-030-34980-6_17
Download citation
DOI: https://doi.org/10.1007/978-3-030-34980-6_17
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-34979-0
Online ISBN: 978-3-030-34980-6
eBook Packages: Computer ScienceComputer Science (R0)