***** To join INSNA, visit http://www.insna.org *****
The JUNG (jung.sourceforge.net) software library is capable of
handling, and running these types of calculation on, very large
networks. It does require some Java programming, but it already has
eigenvector centrality (as a special case of PageRank), and
implementing Bonacich power centrality would not be difficult, given
the source code of the other centrality implementations as models.
(Several other centrality measures are also available in JUNG,
including HITS and betweenness centrality.)
A side note: the interpretation of the results of computing centrality
measures on a bipartite network is not necessarily straightforward
(because the semantics of the entities in each mode are different, but
they are considered to be equivalent from the standpoint of the
centrality algorithm, unless it is specifically designed to operate on
bipartite graphs). You may want to consider whether you should first
convert the graph into a single-mode graph, or interpret the data as a
hypergraph and calculate the measures on that instead. Each of these
is an option in JUNG.
Hope this helps--
On 11/20/06, Hana <[log in to unmask]> wrote:
> ***** To join INSNA, visit http://www.insna.org *****
> Dear all,
> For my dissertation I am trying to compute eigenvector and/or Bonacich
> power centrality on a bipartite network. The data is very large, and too
> much for Ucinet and my (multiple times frozen) computer to handle.
> I've been recommended to use Pajek, but after looking at the manual and
> the book on Exploratory analyses using Pajek, still remain puzzled how to
> do it. A big pardon if I missed an obvious solution, but I would really
> appreciate if you could point me to a "click by click way" to do it.
> Thank you so much in advance, really appreciate the time!
> Big smile and have a great day!!!
> 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.
Joshua O'Madadhain: Information Scientist, Musician, Philosopher-At-Tall
It's that moment of dawning comprehension that I live for. -- Bill Watterson
My opinions are too rational and insightful to be those of any organization.
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.