Full-scale Cascade Dynamics Prediction with a Local-First Approach

TL;DR

This paper introduces FScaleCP, a unified framework for predicting the full temporal evolution of information cascades in social networks by modeling local spreading behaviors and aggregating them through an asynchronous propagation method.

Contribution

It presents a novel approach to predict cascade dynamics at any time point, addressing limitations of previous size-only prediction methods.

Findings

Outperforms state-of-the-art baselines in cascade prediction accuracy

Effectively models local spreading behaviors as a classification problem

Provides a scalable method for full-scale cascade dynamics prediction

Abstract

Information cascades are ubiquitous in various social networking web sites. What mechanisms drive information diffuse in the networks? How does the structure and size of the cascades evolve in time? When and which users will adopt a certain message? Approaching these questions can considerably deepen our understanding about information cascades and facilitate various vital applications, including viral marketing, rumor prevention and even link prediction. Most previous works focus only on the final cascade size prediction. Meanwhile, they are always cascade graph dependent methods, which make them towards large cascades prediction and lead to the criticism that cascades may only be predictable after they have already grown large. In this paper, we study a fundamental problem: full-scale cascade dynamics prediction. That is, how to predict when and which users are activated at any time point of a cascading process. Here we propose a unified framework, FScaleCP, to solve the problem. Given history cascades, we first model the local spreading behaviors as a classification problem. Through data-driven learning, we recognize the common patterns by measuring the driving mechanisms of cascade dynamics. After that we present an intuitive asynchronous propagation method for full-scale cascade dynamics prediction by effectively aggregating the local spreading behaviors. Extensive experiments on social network data set suggest that the proposed method performs noticeably better than other state-of-the-art baselines.