Uncovering and predicting the dynamic process of information cascades with survival model

Linyun Yu, Peng Cui, Fei Wang, Chaoming Song, Shiqiang Yang

Research output: Contribution to journalArticle

5 Citations (Scopus)

Abstract

Cascades are ubiquitous in various network environments. Predicting these cascades is decidedly nontrivial in various important applications, such as viral marketing, epidemic prevention, and traffic management. Most previous works have focused on predicting the final cascade sizes. As cascades are dynamic processes, it is always interesting and important to predict the cascade size at any given time, or to predict the time when a cascade will reach a certain size (e.g., the threshold for an outbreak). In this paper, we unify all these tasks into a fundamental problem: cascading process prediction. That is, given the early stage of a cascade, can we predict its cumulative cascade size at any later time? For such a challenging problem, an understanding of the micromechanism that drives and generates the macrophenomena (i.e., the cascading process) is essential. Here, we introduce behavioral dynamics as the micromechanism to describe the dynamic process of an infected node’s neighbors getting infected by a cascade (i.e., one-hop sub-cascades). Through data-driven analysis, we find out the common principles and patterns lying in the behavioral dynamics and propose the novel NEtworked WEibull Regression model for modeling it. We also propose a novel method for predicting cascading processes by effectively aggregating behavioral dynamics and present a scalable solution to approximate the cascading process with a theoretical guarantee. We evaluate the proposed method extensively on a large-scale social network dataset. The results demonstrate that the proposed method can significantly outperform other state-of-the-art methods in multiple tasks including cascade size prediction, outbreak time prediction, and cascading process prediction.

Original languageEnglish (US)
Pages (from-to)1-27
Number of pages27
JournalKnowledge and Information Systems
DOIs
StateAccepted/In press - May 12 2016

Fingerprint

Marketing

Keywords

  • Dynamic processes prediction
  • Information cascades
  • Social network

ASJC Scopus subject areas

  • Artificial Intelligence
  • Software
  • Information Systems
  • Hardware and Architecture
  • Human-Computer Interaction

Cite this

Uncovering and predicting the dynamic process of information cascades with survival model. / Yu, Linyun; Cui, Peng; Wang, Fei; Song, Chaoming; Yang, Shiqiang.

In: Knowledge and Information Systems, 12.05.2016, p. 1-27.

Research output: Contribution to journalArticle

@article{9854ab2169504b5fa08f0f85766a18a0,
title = "Uncovering and predicting the dynamic process of information cascades with survival model",
abstract = "Cascades are ubiquitous in various network environments. Predicting these cascades is decidedly nontrivial in various important applications, such as viral marketing, epidemic prevention, and traffic management. Most previous works have focused on predicting the final cascade sizes. As cascades are dynamic processes, it is always interesting and important to predict the cascade size at any given time, or to predict the time when a cascade will reach a certain size (e.g., the threshold for an outbreak). In this paper, we unify all these tasks into a fundamental problem: cascading process prediction. That is, given the early stage of a cascade, can we predict its cumulative cascade size at any later time? For such a challenging problem, an understanding of the micromechanism that drives and generates the macrophenomena (i.e., the cascading process) is essential. Here, we introduce behavioral dynamics as the micromechanism to describe the dynamic process of an infected node’s neighbors getting infected by a cascade (i.e., one-hop sub-cascades). Through data-driven analysis, we find out the common principles and patterns lying in the behavioral dynamics and propose the novel NEtworked WEibull Regression model for modeling it. We also propose a novel method for predicting cascading processes by effectively aggregating behavioral dynamics and present a scalable solution to approximate the cascading process with a theoretical guarantee. We evaluate the proposed method extensively on a large-scale social network dataset. The results demonstrate that the proposed method can significantly outperform other state-of-the-art methods in multiple tasks including cascade size prediction, outbreak time prediction, and cascading process prediction.",
keywords = "Dynamic processes prediction, Information cascades, Social network",
author = "Linyun Yu and Peng Cui and Fei Wang and Chaoming Song and Shiqiang Yang",
year = "2016",
month = "5",
day = "12",
doi = "10.1007/s10115-016-0955-7",
language = "English (US)",
pages = "1--27",
journal = "Knowledge and Information Systems",
issn = "0219-1377",
publisher = "Springer London",

}

TY - JOUR

T1 - Uncovering and predicting the dynamic process of information cascades with survival model

AU - Yu, Linyun

AU - Cui, Peng

AU - Wang, Fei

AU - Song, Chaoming

AU - Yang, Shiqiang

PY - 2016/5/12

Y1 - 2016/5/12

N2 - Cascades are ubiquitous in various network environments. Predicting these cascades is decidedly nontrivial in various important applications, such as viral marketing, epidemic prevention, and traffic management. Most previous works have focused on predicting the final cascade sizes. As cascades are dynamic processes, it is always interesting and important to predict the cascade size at any given time, or to predict the time when a cascade will reach a certain size (e.g., the threshold for an outbreak). In this paper, we unify all these tasks into a fundamental problem: cascading process prediction. That is, given the early stage of a cascade, can we predict its cumulative cascade size at any later time? For such a challenging problem, an understanding of the micromechanism that drives and generates the macrophenomena (i.e., the cascading process) is essential. Here, we introduce behavioral dynamics as the micromechanism to describe the dynamic process of an infected node’s neighbors getting infected by a cascade (i.e., one-hop sub-cascades). Through data-driven analysis, we find out the common principles and patterns lying in the behavioral dynamics and propose the novel NEtworked WEibull Regression model for modeling it. We also propose a novel method for predicting cascading processes by effectively aggregating behavioral dynamics and present a scalable solution to approximate the cascading process with a theoretical guarantee. We evaluate the proposed method extensively on a large-scale social network dataset. The results demonstrate that the proposed method can significantly outperform other state-of-the-art methods in multiple tasks including cascade size prediction, outbreak time prediction, and cascading process prediction.

AB - Cascades are ubiquitous in various network environments. Predicting these cascades is decidedly nontrivial in various important applications, such as viral marketing, epidemic prevention, and traffic management. Most previous works have focused on predicting the final cascade sizes. As cascades are dynamic processes, it is always interesting and important to predict the cascade size at any given time, or to predict the time when a cascade will reach a certain size (e.g., the threshold for an outbreak). In this paper, we unify all these tasks into a fundamental problem: cascading process prediction. That is, given the early stage of a cascade, can we predict its cumulative cascade size at any later time? For such a challenging problem, an understanding of the micromechanism that drives and generates the macrophenomena (i.e., the cascading process) is essential. Here, we introduce behavioral dynamics as the micromechanism to describe the dynamic process of an infected node’s neighbors getting infected by a cascade (i.e., one-hop sub-cascades). Through data-driven analysis, we find out the common principles and patterns lying in the behavioral dynamics and propose the novel NEtworked WEibull Regression model for modeling it. We also propose a novel method for predicting cascading processes by effectively aggregating behavioral dynamics and present a scalable solution to approximate the cascading process with a theoretical guarantee. We evaluate the proposed method extensively on a large-scale social network dataset. The results demonstrate that the proposed method can significantly outperform other state-of-the-art methods in multiple tasks including cascade size prediction, outbreak time prediction, and cascading process prediction.

KW - Dynamic processes prediction

KW - Information cascades

KW - Social network

UR - http://www.scopus.com/inward/record.url?scp=84966700854&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84966700854&partnerID=8YFLogxK

U2 - 10.1007/s10115-016-0955-7

DO - 10.1007/s10115-016-0955-7

M3 - Article

SP - 1

EP - 27

JO - Knowledge and Information Systems

JF - Knowledge and Information Systems

SN - 0219-1377

ER -