Mining heterogeneous social networks for egocentric information abstraction

Cheng-Te Li, Shou De Lin

Research output: Chapter in Book/Report/Conference proceedingChapter

Abstract

Social network is a powerful data structure that allows the depiction of relationship information between entities. However, real-world social networks are sometimes too complex for human to pursue further analysis. In this work, an unsupervised mechanism is proposed for egocentric information abstraction in heterogeneous social networks. To achieve this goal, we propose a vector space representation for heterogeneous social networks to identify combination of relations as features and compute statistical dependencies as feature values. These features, either linear or eyelie, intend to capture the semantic information in the surrounding environment of the ego. Then we design three abstraction measures to distill representative and important information to construct the abstracted graphs for visual presentation. The evaluations conducted on a real world movie datasct and an artificial crime dataset demonstrate that the abstractions can indeed retain significant information and facilitate more accurate and efficient human analysis.

Original languageEnglish
Title of host publicationFrom Sociology to Computing in Social Networks
Subtitle of host publicationTheory, Foundations and Applications
PublisherSpringer Vienna
Pages35-58
Number of pages24
ISBN (Print)9783709102930
DOIs
Publication statusPublished - 2010 Dec 1

Fingerprint

Crime
Vector spaces
Data structures
Semantics

All Science Journal Classification (ASJC) codes

  • Computer Science(all)

Cite this

Li, C-T., & Lin, S. D. (2010). Mining heterogeneous social networks for egocentric information abstraction. In From Sociology to Computing in Social Networks: Theory, Foundations and Applications (pp. 35-58). Springer Vienna. https://doi.org/10.1007/978-3-7091-0294-7_3
Li, Cheng-Te ; Lin, Shou De. / Mining heterogeneous social networks for egocentric information abstraction. From Sociology to Computing in Social Networks: Theory, Foundations and Applications. Springer Vienna, 2010. pp. 35-58
@inbook{762cf548916e445badde325908519c6d,
title = "Mining heterogeneous social networks for egocentric information abstraction",
abstract = "Social network is a powerful data structure that allows the depiction of relationship information between entities. However, real-world social networks are sometimes too complex for human to pursue further analysis. In this work, an unsupervised mechanism is proposed for egocentric information abstraction in heterogeneous social networks. To achieve this goal, we propose a vector space representation for heterogeneous social networks to identify combination of relations as features and compute statistical dependencies as feature values. These features, either linear or eyelie, intend to capture the semantic information in the surrounding environment of the ego. Then we design three abstraction measures to distill representative and important information to construct the abstracted graphs for visual presentation. The evaluations conducted on a real world movie datasct and an artificial crime dataset demonstrate that the abstractions can indeed retain significant information and facilitate more accurate and efficient human analysis.",
author = "Cheng-Te Li and Lin, {Shou De}",
year = "2010",
month = "12",
day = "1",
doi = "10.1007/978-3-7091-0294-7_3",
language = "English",
isbn = "9783709102930",
pages = "35--58",
booktitle = "From Sociology to Computing in Social Networks",
publisher = "Springer Vienna",

}

Li, C-T & Lin, SD 2010, Mining heterogeneous social networks for egocentric information abstraction. in From Sociology to Computing in Social Networks: Theory, Foundations and Applications. Springer Vienna, pp. 35-58. https://doi.org/10.1007/978-3-7091-0294-7_3

Mining heterogeneous social networks for egocentric information abstraction. / Li, Cheng-Te; Lin, Shou De.

From Sociology to Computing in Social Networks: Theory, Foundations and Applications. Springer Vienna, 2010. p. 35-58.

Research output: Chapter in Book/Report/Conference proceedingChapter

TY - CHAP

T1 - Mining heterogeneous social networks for egocentric information abstraction

AU - Li, Cheng-Te

AU - Lin, Shou De

PY - 2010/12/1

Y1 - 2010/12/1

N2 - Social network is a powerful data structure that allows the depiction of relationship information between entities. However, real-world social networks are sometimes too complex for human to pursue further analysis. In this work, an unsupervised mechanism is proposed for egocentric information abstraction in heterogeneous social networks. To achieve this goal, we propose a vector space representation for heterogeneous social networks to identify combination of relations as features and compute statistical dependencies as feature values. These features, either linear or eyelie, intend to capture the semantic information in the surrounding environment of the ego. Then we design three abstraction measures to distill representative and important information to construct the abstracted graphs for visual presentation. The evaluations conducted on a real world movie datasct and an artificial crime dataset demonstrate that the abstractions can indeed retain significant information and facilitate more accurate and efficient human analysis.

AB - Social network is a powerful data structure that allows the depiction of relationship information between entities. However, real-world social networks are sometimes too complex for human to pursue further analysis. In this work, an unsupervised mechanism is proposed for egocentric information abstraction in heterogeneous social networks. To achieve this goal, we propose a vector space representation for heterogeneous social networks to identify combination of relations as features and compute statistical dependencies as feature values. These features, either linear or eyelie, intend to capture the semantic information in the surrounding environment of the ego. Then we design three abstraction measures to distill representative and important information to construct the abstracted graphs for visual presentation. The evaluations conducted on a real world movie datasct and an artificial crime dataset demonstrate that the abstractions can indeed retain significant information and facilitate more accurate and efficient human analysis.

UR - http://www.scopus.com/inward/record.url?scp=84889954254&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84889954254&partnerID=8YFLogxK

U2 - 10.1007/978-3-7091-0294-7_3

DO - 10.1007/978-3-7091-0294-7_3

M3 - Chapter

SN - 9783709102930

SP - 35

EP - 58

BT - From Sociology to Computing in Social Networks

PB - Springer Vienna

ER -

Li C-T, Lin SD. Mining heterogeneous social networks for egocentric information abstraction. In From Sociology to Computing in Social Networks: Theory, Foundations and Applications. Springer Vienna. 2010. p. 35-58 https://doi.org/10.1007/978-3-7091-0294-7_3