A Survey of Information Cascade Analysis: Models, Predictions, and Recent Advances

TL;DR

This survey comprehensively reviews models and recent advances in analyzing information cascades, focusing on prediction methods, categorization, and future research challenges in understanding information diffusion.

Contribution

It provides a systematic taxonomy and critical analysis of existing cascade prediction techniques, highlighting gaps and future directions in the field.

Findings

Categorizes cascade prediction methods into feature-based, stochastic, graph, and deep learning approaches.

Identifies strengths and limitations of current models.

Outlines open challenges and opportunities for future research.

Abstract

The deluge of digital information in our daily life -- from user-generated content, such as microblogs and scientific papers, to online business, such as viral marketing and advertising -- offers unprecedented opportunities to explore and exploit the trajectories and structures of the evolution of information cascades. Abundant research efforts, both academic and industrial, have aimed to reach a better understanding of the mechanisms driving the spread of information and quantifying the outcome of information diffusion. This article presents a comprehensive review and categorization of information popularity prediction methods, from feature engineering and stochastic processes, through graph representation, to deep learning-based approaches. Specifically, we first formally define different types of information cascades and summarize the perspectives of existing studies. We then present a taxonomy that categorizes existing works into the aforementioned three main groups as well as the main subclasses in each group, and we systematically review cutting-edge research work. Finally, we summarize the pros and cons of existing research efforts and outline the open challenges and opportunities in this field.