logo

SCIENTIA SINICA Informationis, Volume 48, Issue 11: 1575-1588(2018) https://doi.org/10.1360/N112018-00081

Decentralized cascade dynamics modeling

More info
  • ReceivedApr 9, 2018
  • AcceptedMay 22, 2018
  • PublishedNov 14, 2018

Abstract

Social network platforms have gradually transformed into social media in recent years, which greatly eases information diffusion. Meanwhile, it also makes the task of popularity prediction for online information more challenging. Traditional popularity prediction methods include supervised methods based on feature engineering and popularity dynamics modeling methods based on stochastic processes. The latter group of methods has drawn a wide attention as it works better for predicting individual items' popularity. However, the existing methods have ignored the decentralization characteristic of diffusion cascades. In this paper, we investigate the decentralized structure of diffusion cascades, based on the Weibo dataset, and propose to model cascade dynamics by mixing a bunch of reinforced Poisson processes (RPP). The overall diffusion cascade is a mixture of several sub-cascades, each of which can be modeled by RPP. Experimental results on real world datasets demonstrate our proposed model's superiority in both characterizing popularity dynamics and predicting future popularity.


Funded by

国家重点研发计划项目(2017YFB0803302)

国家自然科学基金(61425016,61472400,61572473)


References

[1] Tatar A, Antoniadis P, Amorim M D. From popularity prediction to ranking online news. Soc Netw Anal Min, 2014, 4: 174 CrossRef Google Scholar

[2] Tatar A, Antoniadis P, De Amorim M D, et al. Ranking news articles based on popularity prediction. In: Proceedings of International Conference on Advances in Social Networks Analysis and Mining, Istanbul, 2012. 106--110. Google Scholar

[3] Chen X, Zhang X D. A popularity-based prediction model for web prefetching. Computer, 2003, 36: 63--70. Google Scholar

[4] Famaey J, Iterbeke F, Wauters T. Towards a predictive cache replacement strategy for multimedia content. J Network Comput Appl, 2013, 36: 219-227 CrossRef Google Scholar

[5] Szabo G, Huberman B A. Predicting the popularity of online content. Commun ACM, 2010, 53: 80--88. Google Scholar

[6] Pinto H, Almeida J M, Gonçalves M A. Using early view patterns to predict the popularity of youtube videos. In: Proceedings of the 6th ACM International Conference on Web Search and Data Mining, Rome, 2013. 365--374. Google Scholar

[7] Tsagkias M, Weerkamp W, de Rijke M. Predicting the volume of comments on online news stories. In: Proceedings of the 18th ACM Conference on Information and Knowledge Management, Hong Kong, 2009. 1765--1768. Google Scholar

[8] Bandari R, Asur S, Huberman B A. The pulse of news in social media: forecasting popularity. In: Proceedings of the 6th International Conference on Weblogs and Social Media, Dublin, 2012. 26--33. Google Scholar

[9] Kong S B, Mei Q Z, Feng L, et al. Predicting bursts and popularity of hashtags in real-time. In: Proceedings of the 37th International ACM SIGIR Conference on Research & Development in Information Retrieval, Gold Coast, 2014. 927--930. Google Scholar

[10] Cui P, Jin S F, Yu L Y, et al. Cascading outbreak prediction in networks: a data-driven approach. In: Proceedings of the 19th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, Chicago, 2013. 901--909. Google Scholar

[11] Bao P, Shen H W, Huang J M, et al. Popularity prediction in microblogging network: a case study on sina weibo. In: Proceedings of the 22nd International Conference on World Wide Web, Rio de Janeiro, 2013. 177--178. Google Scholar

[12] Shulman B, Sharma A, Cosley D. Predictability of popularity: gaps between prediction and understanding. In: Proceedings of the 10th International Conference on Web and Social Media, Cologne, 2016. 348--357. Google Scholar

[13] Andersen P K, Borgan Ø, Hjort N L, et al. Counting process models for life history data: a review. Scand J Stat, 1985, 12: 97--158. Google Scholar

[14] Klein J P, Moeschberger M L. Survival Analysis: Techniques for Censored and Truncated Data. Berlin: Springer, 2005. Google Scholar

[15] Shen H W, Wang D S, Song C M, et al. Modeling and predicting popularity dynamics via reinforced Poisson processes. In: Proceedings of the 28th AAAI Conference on Artificial Intelligence, Québec City, 2014. 291--297. Google Scholar

[16] Gao S, Ma J, Chen Z M. Modeling and predicting retweeting dynamics on microblogging platforms. In: Proceedings of the 8th ACM International Conference on Web Search and Data Mining, Shanghai, 2015. 107--116. Google Scholar

[17] Bao P, Shen H W, Jin X L, et al. Modeling and predicting popularity dynamics of microblogs using self-excited Hawkes processes. In: Proceedings of the 24th International Conference on World Wide Web, Florence, 2015. 9--10. Google Scholar

[18] Zhao Q Y, Erdogdu M A, He H Y, et al. Seismic: a self-exciting point process model for predicting tweet popularity. In: Proceedings of the 21st ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, Sydney, 2015. 1513--1522. Google Scholar

[19] Li C, Ma J Q, Guo X X, et al. Deepcas: an end-to-end predictor of information cascades. In: Proceedings of the 26th International Conference on World Wide Web, Perth, 2017. 577--586. Google Scholar

[20] Cao Q, Shen H W, Cen K T, et al. Deephawkes: bridging the gap between prediction and understanding of information cascades. In: Proceedings of the 26th ACM Conference on Information and Knowledge Management, Singapore, 2017. 1149--1158. Google Scholar

[21] Ouyang S, Li C, Li X. A Peek Into the Future: Predicting the Popularity of Online Videos. IEEE Access, 2016, 4: 3026-3033 CrossRef Google Scholar

[22] Cao Q, Shen H W, Gao H, et al. Predicting the popularity of online content with group-specific models. In: Proceedings of the 26th International Conference on World Wide Web Companion, Perth, 2017. 765--766. Google Scholar

[23] Gao J H, Shen H W, Liu S H, et al. Modeling and predicting retweeting dynamics via a mixture process. In: Proceedings of the 25th International Conference Companion on World Wide Web, Montréal, 2016. 33--34. Google Scholar

[24] Iyengar R, Van den Bulte C, Valente T W. Opinion Leadership and Social Contagion in New Product Diffusion. Marketing Sci, 2011, 30: 195-212 CrossRef Google Scholar

[25] Staab S, Domingos P, Mika P. Social Networks Applied. IEEE Intell Syst, 2005, 20: 80-93 CrossRef Google Scholar

[26] Crane R, Sornette D. Robust dynamic classes revealed by measuring the response function of a social system. Proc Natl Acad Sci USA, 2008, 105: 15649-15653 CrossRef PubMed ADS arXiv Google Scholar

[27] Jeong H, Néda Z, Barabási A L. Measuring preferential attachment in evolving networks. Europhys Lett, 2003, 61: 567-572 CrossRef ADS Google Scholar

[28] Wang M, Yu G, Yu D. Measuring the preferential attachment mechanism in citation networks. Physica A-Statistical Mech its Appl, 2008, 387: 4692-4698 CrossRef ADS Google Scholar

[29] Zeiler M D. Adadelta: an adaptive learning rate method. 2012,. arXiv Google Scholar

Copyright 2019 Science China Press Co., Ltd. 《中国科学》杂志社有限责任公司 版权所有

京ICP备18024590号-1