Spectral analysis of social networks to identify periodicity

Two key problems in the study of longitudinal networks are determining when to chunk continuoustime data into discrete time periods for network analysis and identifying periodicity in the data. In addition, statistical process control applied to longitudinal social network measures can be biased by...

Full description

Bibliographic Details
Main Authors: McCulloh, Ian, Johnson, A., Carley, K.
Format: Journal Article
Published: Taylor & Francis 2012
Subjects:
Online Access:http://www.tandfonline.com/toc/gmas20/current
http://hdl.handle.net/20.500.11937/49333
_version_ 1848758218338074624
author McCulloh, Ian
Johnson, A.
Carley, K.
author_facet McCulloh, Ian
Johnson, A.
Carley, K.
author_sort McCulloh, Ian
building Curtin Institutional Repository
collection Online Access
description Two key problems in the study of longitudinal networks are determining when to chunk continuoustime data into discrete time periods for network analysis and identifying periodicity in the data. In addition, statistical process control applied to longitudinal social network measures can be biased by the effects of relational dependence and periodicity in the data. Thus, the detection of change is often obscured by random noise. Fourier analysis is used to determine statistically significant periodic frequencies in longitudinal network data. Two approaches are then offered: using significant periods as a basis to chunk data for longitudinal network analysis or using the significant periods to filter the longitudinal data. E-mail communication collected at the United States Military Academy is examined.
first_indexed 2025-11-14T09:40:30Z
format Journal Article
id curtin-20.500.11937-49333
institution Curtin University Malaysia
institution_category Local University
last_indexed 2025-11-14T09:40:30Z
publishDate 2012
publisher Taylor & Francis
recordtype eprints
repository_type Digital Repository
spelling curtin-20.500.11937-493332017-03-15T22:56:12Z Spectral analysis of social networks to identify periodicity McCulloh, Ian Johnson, A. Carley, K. statistical process control longitudinal networks Fourier analysis network dynamics social network analysis Two key problems in the study of longitudinal networks are determining when to chunk continuoustime data into discrete time periods for network analysis and identifying periodicity in the data. In addition, statistical process control applied to longitudinal social network measures can be biased by the effects of relational dependence and periodicity in the data. Thus, the detection of change is often obscured by random noise. Fourier analysis is used to determine statistically significant periodic frequencies in longitudinal network data. Two approaches are then offered: using significant periods as a basis to chunk data for longitudinal network analysis or using the significant periods to filter the longitudinal data. E-mail communication collected at the United States Military Academy is examined. 2012 Journal Article http://hdl.handle.net/20.500.11937/49333 http://www.tandfonline.com/toc/gmas20/current Taylor & Francis restricted
spellingShingle statistical process control
longitudinal networks
Fourier analysis
network dynamics
social network analysis
McCulloh, Ian
Johnson, A.
Carley, K.
Spectral analysis of social networks to identify periodicity
title Spectral analysis of social networks to identify periodicity
title_full Spectral analysis of social networks to identify periodicity
title_fullStr Spectral analysis of social networks to identify periodicity
title_full_unstemmed Spectral analysis of social networks to identify periodicity
title_short Spectral analysis of social networks to identify periodicity
title_sort spectral analysis of social networks to identify periodicity
topic statistical process control
longitudinal networks
Fourier analysis
network dynamics
social network analysis
url http://www.tandfonline.com/toc/gmas20/current
http://hdl.handle.net/20.500.11937/49333