Abstract

This study of collective behavior is to understand how individuals behave in a social networking environment. Oceans of data generated by social media like Facebook, Twitter, Flickr, and YouTube present opportunities and challenges to study collective behavior on a large scale. In this work, we aim to learn to predict collective behavior in social media. In particular, given information about some individuals, how can we infer the behavior of unobserved individuals in the same network? A social-dimension-based approach has been shown effective in addressing the heterogeneity of connections presented in social media. However, the networks in social media are normally of colossal size, involving hundreds of thousands of actors. The scale of these networks entails scalable learning of models for collective behavior prediction. To address the scalability issue, we propose an edge-centric clustering scheme to extract sparse social dimensions. With sparse social dimensions, the proposed approach can efficiently handle networks of millions of actors while demonstrating a comparable prediction performance to other nonscalable methods.

Original languageEnglish (US)
Article number5710923
Pages (from-to)1080-1091
Number of pages12
JournalIEEE Transactions on Knowledge and Data Engineering
Volume24
Issue number6
DOIs
StatePublished - 2012

Fingerprint

Scalability

Keywords

  • Classification with network data
  • collective behavior
  • community detection
  • social dimensions

ASJC Scopus subject areas

  • Computational Theory and Mathematics
  • Information Systems
  • Computer Science Applications

Cite this

Scalable learning of collective behavior. / Tang, Lei; Wang, Xufei; Liu, Huan.

In: IEEE Transactions on Knowledge and Data Engineering, Vol. 24, No. 6, 5710923, 2012, p. 1080-1091.

Research output: Contribution to journalArticle

Tang, Lei ; Wang, Xufei ; Liu, Huan. / Scalable learning of collective behavior. In: IEEE Transactions on Knowledge and Data Engineering. 2012 ; Vol. 24, No. 6. pp. 1080-1091.
@article{bbc96e4a3251418f84df1ccde3e07486,
title = "Scalable learning of collective behavior",
abstract = "This study of collective behavior is to understand how individuals behave in a social networking environment. Oceans of data generated by social media like Facebook, Twitter, Flickr, and YouTube present opportunities and challenges to study collective behavior on a large scale. In this work, we aim to learn to predict collective behavior in social media. In particular, given information about some individuals, how can we infer the behavior of unobserved individuals in the same network? A social-dimension-based approach has been shown effective in addressing the heterogeneity of connections presented in social media. However, the networks in social media are normally of colossal size, involving hundreds of thousands of actors. The scale of these networks entails scalable learning of models for collective behavior prediction. To address the scalability issue, we propose an edge-centric clustering scheme to extract sparse social dimensions. With sparse social dimensions, the proposed approach can efficiently handle networks of millions of actors while demonstrating a comparable prediction performance to other nonscalable methods.",
keywords = "Classification with network data, collective behavior, community detection, social dimensions",
author = "Lei Tang and Xufei Wang and Huan Liu",
year = "2012",
doi = "10.1109/TKDE.2011.38",
language = "English (US)",
volume = "24",
pages = "1080--1091",
journal = "IEEE Transactions on Knowledge and Data Engineering",
issn = "1041-4347",
publisher = "IEEE Computer Society",
number = "6",

}

TY - JOUR

T1 - Scalable learning of collective behavior

AU - Tang, Lei

AU - Wang, Xufei

AU - Liu, Huan

PY - 2012

Y1 - 2012

N2 - This study of collective behavior is to understand how individuals behave in a social networking environment. Oceans of data generated by social media like Facebook, Twitter, Flickr, and YouTube present opportunities and challenges to study collective behavior on a large scale. In this work, we aim to learn to predict collective behavior in social media. In particular, given information about some individuals, how can we infer the behavior of unobserved individuals in the same network? A social-dimension-based approach has been shown effective in addressing the heterogeneity of connections presented in social media. However, the networks in social media are normally of colossal size, involving hundreds of thousands of actors. The scale of these networks entails scalable learning of models for collective behavior prediction. To address the scalability issue, we propose an edge-centric clustering scheme to extract sparse social dimensions. With sparse social dimensions, the proposed approach can efficiently handle networks of millions of actors while demonstrating a comparable prediction performance to other nonscalable methods.

AB - This study of collective behavior is to understand how individuals behave in a social networking environment. Oceans of data generated by social media like Facebook, Twitter, Flickr, and YouTube present opportunities and challenges to study collective behavior on a large scale. In this work, we aim to learn to predict collective behavior in social media. In particular, given information about some individuals, how can we infer the behavior of unobserved individuals in the same network? A social-dimension-based approach has been shown effective in addressing the heterogeneity of connections presented in social media. However, the networks in social media are normally of colossal size, involving hundreds of thousands of actors. The scale of these networks entails scalable learning of models for collective behavior prediction. To address the scalability issue, we propose an edge-centric clustering scheme to extract sparse social dimensions. With sparse social dimensions, the proposed approach can efficiently handle networks of millions of actors while demonstrating a comparable prediction performance to other nonscalable methods.

KW - Classification with network data

KW - collective behavior

KW - community detection

KW - social dimensions

UR - http://www.scopus.com/inward/record.url?scp=84860466575&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84860466575&partnerID=8YFLogxK

U2 - 10.1109/TKDE.2011.38

DO - 10.1109/TKDE.2011.38

M3 - Article

AN - SCOPUS:84860466575

VL - 24

SP - 1080

EP - 1091

JO - IEEE Transactions on Knowledge and Data Engineering

JF - IEEE Transactions on Knowledge and Data Engineering

SN - 1041-4347

IS - 6

M1 - 5710923

ER -