Modeling and Predicting Popularity Dynamics of Microblogs using Self-Excited Hawkes Processes

Bao, Peng; Shen, Huawei; Jin, Xiaolong; Cheng, Xueqi

doi:10.1145/2740908.2742744

Cited by 81 publications

(37 citation statements)

References 3 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…This section focuses on a system of stochastic partial differential equations (SPDE), introduced and studied in [13] where some qualitative properties are discussed. The SPDE is a noisy version of the PDE system (4) and is expected to be a more precise approximation of the age-dependent Hawkes processes in a mean-field framework.…”

Section: Application To the "Almost" Derivation Of An Spdementioning

confidence: 99%

“…In the recent years, the self-exciting point process known as the Hawkes process [20] has been used in very diverse areas. First introduced to model earthquake replicas [24] or [31] (ETAS model), it has been used in criminology to model burglary [30], in genomic data analysis to model occurrences of genes [19,36], in social networks analysis to model viewing or popularity [4,12], as well as in finance [2,3]. We refer to [25] or [43] for more extensive reviews on applications of Hawkes processes.…”

Section: Introductionmentioning

confidence: 99%

“…Hence, the derivation of the second order term is of great importance regarding neural networks modelling since it gives an approximation of the fluctuations coming from the finiteness of the number of neurons n (finite size effects) [7,8,27]. A partial but promising answer to this problematic is given by highlighting a stochastic partial differential equation system which could be interpreted as an intermediate modelling scale between the microscopic scale given by ADHP and the macroscopic one given by (4).…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Fluctuations for mean-field interacting age-dependent Hawkes processes

Chevallier¹

2017

Electron. J. Probab.

View full text Add to dashboard Cite

The propagation of chaos and associated law of large numbers for mean-field interacting age-dependent Hawkes processes (when the number of processes n goes to +∞) being granted by the study performed in [9], the aim of the present paper is to prove the resulting functional central limit theorem. It involves the study of a measure-valued process describing the fluctuations (at scale n −1/2 ) of the empirical measure of the ages around its limit value. This fluctuation process is proved to converge towards a limit process characterized by a limit system of stochastic differential equations driven by a Gaussian noise instead of Poisson (which occurs for the law of large numbers limit). t 0 h(t − z)u(z, 0)dz [9, Proposition III.8.]. Such a form of PDE system is known either as age-structure system or refractory density equation or even von Foerster-McKendrick system. Here, the age is represented by the variable s. We refer to [14] for a linear version of (4) and its theoretical connection with the integrate and fire model, and to [17,32,33] for analytical studies of (4).The relation between mean-field age dependent Hawkes processes and the PDE system (4) is completed by the following law of large numbers (consequence of the functional law of large numbers [9, Corollary IV.4.]):

show abstract

Section: Application To the "Almost" Derivation Of An Spdementioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Fluctuations for mean-field interacting age-dependent Hawkes processes

Chevallier¹

2017

Electron. J. Probab.

View full text Add to dashboard Cite

show abstract

“…Pozdnoukhov and Kaiser (2011) use a Markov-modulated Poisson process, in which h(t) varies according to a Markov process, in their application of identification and spatiotemporal analysis of topics on Twitter. Bao et al (2015) propose a self-excited Hawkes process (SEHP), in which h(t) jumps simultaneously when an event occurs and decays before the next event occurs, and argue that such their model outperforms the one by Shen et al (2014), in terms of prediction accuracy, when applied to the same set of data.…”

Section: Temporal Dynamicsmentioning

confidence: 98%

A Hierarchical Model of Nonhomogeneous Poisson Processes for Twitter Retweets

Lee

Wilkinson

2019

Journal of the American Statistical Association

View full text Add to dashboard Cite

We present a hierarchical model of non-homogeneous Poisson processes (NHPP) for information diffusion on online social media, in particular Twitter retweets. The retweets of each original tweet are modelled by a NHPP, for which the intensity function is a product of time-decaying components and another component that depends on the follower count of the original tweet author. The latter allows us to explain or predict the ultimate retweet count by a network centrality-related covariate. The inference algorithm enables the Bayes factor to be computed, in order to facilitate model selection. Finally, the model is applied to the retweet data sets of two hashtags.

show abstract

“…We and studied how different video referrers impact the popularity of an individual video. Bao et al [15] used the self-excited Hawkes processes to model the popularity evolution of an individual microblog.…”

mentioning

confidence: 99%

Analysis and prediction of content popularity for online video service: a Youku case study

Ouyang

2016

China Commun.

View full text Add to dashboard Cite

In recent years, the ubiquitous Web 2.0 services have brought along an enormous and ever growing amount of video content onto the Internet. Meanwhile, the emerging online social networking (OSN) services are helping distribute those massive videos all through the Internet. As noted by the white paper of Cisco [1], it would take an individual over 5 million years to watch the all videos across the global IP networks each month. Since the attention and time of users are limited, it is not surprising that the popularity of those online videos usually distributes in a rather asymmetric way: a small number of videos receive the majority of views, while most of the videos are barely noticed [2] [3].Given the large content volume and the uneven user attention, understanding the characteristics of online video popularity as well as predicting the future video popularity are of great importance for many reasons. For in-Abstract: Understanding the characteristics and predicting the popularity of the newly published online videos can provide direct implications in various contexts such as service design, advertisement planning, network management and etc. In this paper, we collect a real-world large-scale dataset from a leading online video service provider in China, of content publication and content popularity for the online video service. Then, we propose a rich set of features and exploit various effective classification methods to estimate the future popularity level of an individual video in various scenarios. We show that the future popularity level of a video can be predicted even before the video's release, and by introducing the historical popularity information the prediction performance can be improved dramatically. In addition, we investigate the importance of each feature group and each feature in the popularity prediction, and further reveal the factors that may impact the video popularity. We also discuss how the early monitoring period influences the popularity level prediction. Our work provides an insight into the popularity of the newly published online videos, and demonstrates promising practical applications for content publishers, SERVICES AND APPLICATIONS217 eo is closely related to its future popularity.ularity of an individual video or not? Based on the analysis and domain knowledge, we propose a rich set of features related to online video popularity. We want to know to the feasibility of predicting the future video popularity with these features and effective classification methods in different scenarios. Moreover, we want to know to what extent we can improve the prediction by monitoring an early period of popularity evolution for an individual video. In addition, we tend to reveal how different factors impact the popularity of online videos. Those important factors for predicting the video popularity should be taken into account for the future service design.The main contributions of our work are summarized as follows:scale and long-term dataset for the online video popularity study. We should ...

show abstract

Modeling and Predicting Popularity Dynamics of Microblogs using Self-Excited Hawkes Processes

Cited by 81 publications

References 3 publications

Fluctuations for mean-field interacting age-dependent Hawkes processes

Fluctuations for mean-field interacting age-dependent Hawkes processes

A Hierarchical Model of Nonhomogeneous Poisson Processes for Twitter Retweets

Analysis and prediction of content popularity for online video service: a Youku case study

Contact Info

Product

Resources

About