TiDeH: Time-Dependent Hawkes Process for Predicting Retweet Dynamics
TiDeH: Time-Dependent Hawkes Process for Predicting Retweet Dynamics
复制标题
DOI：
10.1609/icwsm.v10i1.14717
复制
发表时间：
2016-03
期刊：
影响因子：
--
通讯作者：
Ryota Kobayashi;R. Lambiotte
中科院分区：
文献类型：
--
作者：
Ryota Kobayashi;R. Lambiotte
在线社交网络服务允许其用户以文本、图像或视频的形式发布内容。推动内容传播的主要机制是用户重新分享其社交关系发布的内容的可能性，然后这些内容可能会在整个系统中级联。研究信息级联的一个基本问题是，能否建立可靠的数学模型，其参数可根据经验数据加以校准，以便预测一段时间的观测之后级联的未来走向。在本文中，我们专注于Twitter，特别是对原始推文的转发活动的时间模式。我们采用时间依赖霍克斯过程（Time-Dependent Hawkes Process，TiDeH）对系统进行建模，该模型充分考虑了用户的昼夜节律和信息的老化。预测模型的输入是观察到的转发次数和关于底层社交网络的结构信息。我们开发了一个程序参数优化和预测未来的配置文件的转推活动在不同的时间分辨率。我们验证了我们的方法在一个大型语料库的Twitter数据，并证明其系统的改进，在所有的时间制度，现有的方法。
Online social networking services allow their users to post content in the form of text, images or videos. The main mechanism driving content diffusion is the possibility for users to re-share the content posted by their social connections, which may then cascade across the system. A fundamental problem when studying information cascades is the possibility to develop sound mathematical models, whose parameters can be calibrated on empirical data, in order to predict the future course of a cascade after a window of observation. In this paper, we focus on Twitter and, in particular, on the temporal patterns of retweet activity for an original tweet. We model the system by Time-Dependent Hawkes process (TiDeH), which properly takes into account the circadian nature of the users and the aging of information. The input of the prediction model are observed retweet times and structural information about the underlying social network. We develop a procedure for parameter optimization and for predicting the future profiles of retweet activity at different time resolutions. We validate our methodology on a large corpus of Twitter data and demonstrate its systematic improvement over existing approaches in all the time regimes.