Print

Print


*****  To join INSNA, visit http://www.insna.org  *****

Dear Gohar Kahn, 

 

In a study with Rob Goldstone about evolving citation patterns as indicators
of cognitive organization in the case of Cognitive Science (at
http://arxiv.org/abs/1212.0823 ), we use four-year moving aggregates in
order to dampen the yearly fluctuations.  Co-authorship relations may be of
the same type.

 

I would also include the latent dimensions of the vector space using factor
analysis of the (asymmetrical) documents/authors matrix or community finding
algorithms in the coauthor matrices (Blondel). 

 

Best,

Loet

 

  _____  

Loet Leydesdorff 

Professor, University of Amsterdam
Amsterdam School of Communications Research (ASCoR)

Kloveniersburgwal 48, 1012 CX Amsterdam
 <mailto:[log in to unmask]> [log in to unmask] ;
<http://www.leydesdorff.net/> http://www.leydesdorff.net/ 
Honorary Professor, SPRU,  <http://www.sussex.ac.uk/spru/> University of
Sussex; Visiting Professor, ISTIC,
<http://www.istic.ac.cn/Eng/brief_en.html> Beijing;
http://scholar.google.com/citations?user=ych9gNYAAAAJ
<http://scholar.google.com/citations?user=ych9gNYAAAAJ&hl=en> &hl=en  



 

From: Social Networks Discussion Forum [mailto:[log in to unmask]] On
Behalf Of G.F.Khan
Sent: Tuesday, September 17, 2013 1:29 PM
To: [log in to unmask]
Subject: Longitudinal co-authorship network analysis

 

***** To join INSNA, visit http://www.insna.org ***** 

Hello Group members,

 

Which network parameters (apart from density, degree, and clustering
coefficient) should one compare when investigating longitudinal patterns in
a network (e.g., in a co-authorship network of researchers in a scientific
domain captured at a fix 10 years intervals)? We are interested more to see
how the co-authorship network is evolving over time e.g., is the network
becoming more/less efficient and/or effective? We are interested in
capturing and comparing any parameters that can shed light on the evolution
of the network (e.g., using UNINET or Pajek).

 

One another relevant question may be what should one consider when deciding
on partitioning the network data into fix intervals? Lets say we have
longitudinal co-authorship data from 1970 to 2012, how should we partition
this data to best capture the network evaluation?

 

Any suggestions are welcomed.

 

Thank you,

 

 

-- 

Khan, Gohar Feroz (PhD)
Assistant Professor
Korea University of Technology & Education (KoreaTECH)
1600 Chungjol-ro Byungcheon-myun
Cheonan city, 330-708, South Korea
Office: 82-41-560-1415; Mobile: +82-10-5510-8071
email: [log in to unmask] 
-------------------------------------------------------

Director Center for Social Technologies
<http://sminsight.wordpress.com/about-2/> 
Associate Editor Journal of Contemporary Eastern Asia
<http://eastasia.yu.ac.kr/>  
I blog here <http://gfkhan.wordpress.com/dr-khan/> 

---------------------------------------------------------------------

_____________________________________________________________________ SOCNET
is a service of INSNA, the professional association for social network
researchers (http://www.insna.org). To unsubscribe, send an email message to
[log in to unmask] containing the line UNSUBSCRIBE SOCNET in the body of
the message. 


_____________________________________________________________________
SOCNET is a service of INSNA, the professional association for social
network researchers (http://www.insna.org). To unsubscribe, send
an email message to [log in to unmask] containing the line
UNSUBSCRIBE SOCNET in the body of the message.