TiDeH: Time-Dependent Hawkes Process for Predicting Retweet Dynamics

TL;DR

This paper introduces TiDeH, a time-dependent Hawkes process model that predicts retweet dynamics on Twitter by accounting for circadian patterns and information aging, validated on large-scale data.

Contribution

The paper presents a novel TiDeH model that incorporates circadian and aging effects for retweet prediction, with a new parameter optimization procedure.

Findings

Systematic improvement over existing models across all time regimes.

Effective prediction of retweet activity profiles.

Validated on large Twitter datasets.

Abstract

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.