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

TL;DR

This paper introduces a probabilistic Self-Excited Hawkes Process model to accurately predict the popularity growth of microblogs by explicitly modeling individual forwarding effects, validated on Sina Weibo data.

Contribution

The paper presents a novel SEHP model that explicitly captures individual forwarding effects, improving prediction accuracy over previous reinforced Poisson process models.

Findings

SEHP outperforms reinforced Poisson process models in predicting microblog popularity.

Experimental validation on Sina Weibo shows improved modeling of forwarding dynamics.

The model effectively captures the triggering effect of each forwarding event.

Abstract

The ability to model and predict the popularity dynamics of individual user generated items on online media has important implications in a wide range of areas. In this paper, we propose a probabilistic model using a Self-Excited Hawkes Process(SEHP) to characterize the process through which individual microblogs gain their popularity. This model explicitly captures the triggering effect of each forwarding, distinguishing itself from the reinforced Poisson process based model where all previous forwardings are simply aggregated as a single triggering effect. We validate the proposed model by applying it on Sina Weibo, the most popular microblogging network in China. Experimental results demonstrate that the SEHP model consistently outperforms the model based on reinforced Poisson process.