Mining dynamic social networks from public news articles for company value prediction

Yingzi Jin, Ching Yung Lin, Yutaka Matsuo, Mitsuru Ishizuka

Research output: Contribution to journalArticle

21 Citations (Scopus)

Abstract

Dynamic networks are studied by sociologists to understand network evolution, belief formation, friendship formation, etc. Companies make and receive different impacts from other companies in different periods. If one can understand what types of network changes affect a company’s value, then one would be able to predict the future value of the company, grasp industry innovations, and make business more successful. However, it is often difficult to collect continuous records of network changes, and the models of mining longitudinal network are complicated. In this study, we developed algorithms and a system to infer large-scale evolutionary company networks from public news during 1981–2009. Then, based on how networks change over time, and on the financial information of the companies, we predicted company profit and revenue growth. Herein, we propose a feature extraction and selection algorithm for longitudinal networks. This paper is the first to describe a study examining longitudinal network-mining-based company performance analysis. We measured how networks affect company performance and what network features are important.

Original languageEnglish
Pages (from-to)217-228
Number of pages12
JournalSocial Network Analysis and Mining
Volume2
Issue number3
DOIs
Publication statusPublished - 2012 Jan 1
Externally publishedYes

Fingerprint

social network
news
Values
Industry
Feature extraction
sociologist
friendship
Profitability
performance
Innovation
revenue
longitudinal study
profit
innovation
industry

Keywords

  • Company value
  • Dynamic social network
  • Feature selection
  • Relation extraction
  • Social network analysis

ASJC Scopus subject areas

  • Computer Science Applications
  • Human-Computer Interaction
  • Information Systems
  • Communication
  • Media Technology

Cite this

Mining dynamic social networks from public news articles for company value prediction. / Jin, Yingzi; Lin, Ching Yung; Matsuo, Yutaka; Ishizuka, Mitsuru.

In: Social Network Analysis and Mining, Vol. 2, No. 3, 01.01.2012, p. 217-228.

Research output: Contribution to journalArticle

Jin, Yingzi ; Lin, Ching Yung ; Matsuo, Yutaka ; Ishizuka, Mitsuru. / Mining dynamic social networks from public news articles for company value prediction. In: Social Network Analysis and Mining. 2012 ; Vol. 2, No. 3. pp. 217-228.
@article{4d0ead8b70b540ed819d2afa61bbc5df,
title = "Mining dynamic social networks from public news articles for company value prediction",
abstract = "Dynamic networks are studied by sociologists to understand network evolution, belief formation, friendship formation, etc. Companies make and receive different impacts from other companies in different periods. If one can understand what types of network changes affect a company’s value, then one would be able to predict the future value of the company, grasp industry innovations, and make business more successful. However, it is often difficult to collect continuous records of network changes, and the models of mining longitudinal network are complicated. In this study, we developed algorithms and a system to infer large-scale evolutionary company networks from public news during 1981–2009. Then, based on how networks change over time, and on the financial information of the companies, we predicted company profit and revenue growth. Herein, we propose a feature extraction and selection algorithm for longitudinal networks. This paper is the first to describe a study examining longitudinal network-mining-based company performance analysis. We measured how networks affect company performance and what network features are important.",
keywords = "Company value, Dynamic social network, Feature selection, Relation extraction, Social network analysis",
author = "Yingzi Jin and Lin, {Ching Yung} and Yutaka Matsuo and Mitsuru Ishizuka",
year = "2012",
month = "1",
day = "1",
doi = "10.1007/s13278-011-0045-5",
language = "English",
volume = "2",
pages = "217--228",
journal = "Social Network Analysis and Mining",
issn = "1869-5450",
publisher = "Springer Wien",
number = "3",

}

TY - JOUR

T1 - Mining dynamic social networks from public news articles for company value prediction

AU - Jin, Yingzi

AU - Lin, Ching Yung

AU - Matsuo, Yutaka

AU - Ishizuka, Mitsuru

PY - 2012/1/1

Y1 - 2012/1/1

N2 - Dynamic networks are studied by sociologists to understand network evolution, belief formation, friendship formation, etc. Companies make and receive different impacts from other companies in different periods. If one can understand what types of network changes affect a company’s value, then one would be able to predict the future value of the company, grasp industry innovations, and make business more successful. However, it is often difficult to collect continuous records of network changes, and the models of mining longitudinal network are complicated. In this study, we developed algorithms and a system to infer large-scale evolutionary company networks from public news during 1981–2009. Then, based on how networks change over time, and on the financial information of the companies, we predicted company profit and revenue growth. Herein, we propose a feature extraction and selection algorithm for longitudinal networks. This paper is the first to describe a study examining longitudinal network-mining-based company performance analysis. We measured how networks affect company performance and what network features are important.

AB - Dynamic networks are studied by sociologists to understand network evolution, belief formation, friendship formation, etc. Companies make and receive different impacts from other companies in different periods. If one can understand what types of network changes affect a company’s value, then one would be able to predict the future value of the company, grasp industry innovations, and make business more successful. However, it is often difficult to collect continuous records of network changes, and the models of mining longitudinal network are complicated. In this study, we developed algorithms and a system to infer large-scale evolutionary company networks from public news during 1981–2009. Then, based on how networks change over time, and on the financial information of the companies, we predicted company profit and revenue growth. Herein, we propose a feature extraction and selection algorithm for longitudinal networks. This paper is the first to describe a study examining longitudinal network-mining-based company performance analysis. We measured how networks affect company performance and what network features are important.

KW - Company value

KW - Dynamic social network

KW - Feature selection

KW - Relation extraction

KW - Social network analysis

UR - http://www.scopus.com/inward/record.url?scp=84880711388&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84880711388&partnerID=8YFLogxK

U2 - 10.1007/s13278-011-0045-5

DO - 10.1007/s13278-011-0045-5

M3 - Article

VL - 2

SP - 217

EP - 228

JO - Social Network Analysis and Mining

JF - Social Network Analysis and Mining

SN - 1869-5450

IS - 3

ER -