Trend mining in social networks

From trend identification to visualization

Nohuddin Puteri Nor Ellyza, Wataru Sunayama, Rob Christley, Frans Coenen, Christian Setzkorn

Research output: Contribution to journalArticle

2 Citations (Scopus)

Abstract

A four-stage social network trend mining framework, the Identification, Grouping, Clustering and Visualization framework, is described. The framework extracts trends from social network data and then applies a sequence of techniques ('tools') to this data to facilitate interpretation of the identified trends. Of particular note is the visualization of trend migrations (changes) that feature within time-stamped network data. The framework is illustrated using a sequence of four social networks extracted from the Cattle Tracing System in operation in Great Britain, although it could equally well be applied to other forms of temporal data. The presented analysis of the Identification, Grouping, Clustering and Visualization framework indicates advantages, with respect to network trend mining, that can be gained, especially when the framework is applied to real data.

Original languageEnglish
Pages (from-to)457-468
Number of pages12
JournalExpert Systems
Volume31
Issue number5
DOIs
Publication statusPublished - 1 Nov 2014
Externally publishedYes

Fingerprint

Social Networks
Mining
Visualization
Grouping
Clustering
Tracing
Migration
Framework
Trends

Keywords

  • Social network data
  • Trend mining
  • Visualization

ASJC Scopus subject areas

  • Control and Systems Engineering
  • Artificial Intelligence
  • Theoretical Computer Science
  • Computational Theory and Mathematics

Cite this

Trend mining in social networks : From trend identification to visualization. / Puteri Nor Ellyza, Nohuddin; Sunayama, Wataru; Christley, Rob; Coenen, Frans; Setzkorn, Christian.

In: Expert Systems, Vol. 31, No. 5, 01.11.2014, p. 457-468.

Research output: Contribution to journalArticle

Puteri Nor Ellyza, Nohuddin ; Sunayama, Wataru ; Christley, Rob ; Coenen, Frans ; Setzkorn, Christian. / Trend mining in social networks : From trend identification to visualization. In: Expert Systems. 2014 ; Vol. 31, No. 5. pp. 457-468.
@article{5b622c146ec64d3aa7ab0e87612e5668,
title = "Trend mining in social networks: From trend identification to visualization",
abstract = "A four-stage social network trend mining framework, the Identification, Grouping, Clustering and Visualization framework, is described. The framework extracts trends from social network data and then applies a sequence of techniques ('tools') to this data to facilitate interpretation of the identified trends. Of particular note is the visualization of trend migrations (changes) that feature within time-stamped network data. The framework is illustrated using a sequence of four social networks extracted from the Cattle Tracing System in operation in Great Britain, although it could equally well be applied to other forms of temporal data. The presented analysis of the Identification, Grouping, Clustering and Visualization framework indicates advantages, with respect to network trend mining, that can be gained, especially when the framework is applied to real data.",
keywords = "Social network data, Trend mining, Visualization",
author = "{Puteri Nor Ellyza}, Nohuddin and Wataru Sunayama and Rob Christley and Frans Coenen and Christian Setzkorn",
year = "2014",
month = "11",
day = "1",
doi = "10.1111/exsy.12024",
language = "English",
volume = "31",
pages = "457--468",
journal = "Expert Systems",
issn = "0266-4720",
publisher = "Wiley-Blackwell",
number = "5",

}

TY - JOUR

T1 - Trend mining in social networks

T2 - From trend identification to visualization

AU - Puteri Nor Ellyza, Nohuddin

AU - Sunayama, Wataru

AU - Christley, Rob

AU - Coenen, Frans

AU - Setzkorn, Christian

PY - 2014/11/1

Y1 - 2014/11/1

N2 - A four-stage social network trend mining framework, the Identification, Grouping, Clustering and Visualization framework, is described. The framework extracts trends from social network data and then applies a sequence of techniques ('tools') to this data to facilitate interpretation of the identified trends. Of particular note is the visualization of trend migrations (changes) that feature within time-stamped network data. The framework is illustrated using a sequence of four social networks extracted from the Cattle Tracing System in operation in Great Britain, although it could equally well be applied to other forms of temporal data. The presented analysis of the Identification, Grouping, Clustering and Visualization framework indicates advantages, with respect to network trend mining, that can be gained, especially when the framework is applied to real data.

AB - A four-stage social network trend mining framework, the Identification, Grouping, Clustering and Visualization framework, is described. The framework extracts trends from social network data and then applies a sequence of techniques ('tools') to this data to facilitate interpretation of the identified trends. Of particular note is the visualization of trend migrations (changes) that feature within time-stamped network data. The framework is illustrated using a sequence of four social networks extracted from the Cattle Tracing System in operation in Great Britain, although it could equally well be applied to other forms of temporal data. The presented analysis of the Identification, Grouping, Clustering and Visualization framework indicates advantages, with respect to network trend mining, that can be gained, especially when the framework is applied to real data.

KW - Social network data

KW - Trend mining

KW - Visualization

UR - http://www.scopus.com/inward/record.url?scp=84911002106&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84911002106&partnerID=8YFLogxK

U2 - 10.1111/exsy.12024

DO - 10.1111/exsy.12024

M3 - Article

VL - 31

SP - 457

EP - 468

JO - Expert Systems

JF - Expert Systems

SN - 0266-4720

IS - 5

ER -