***** To join INSNA, visit http://www.insna.org *****
I wonder if the group could help a newcomer with advice on some fundamental tasks, like a "Getting Started with Social Network Analysis"?
I have been gathering information about a certain group of social media users and which ones of them follow one another. We have about 15 million individuals in this network which has very high connection groups within the overall network (72 million connections between them). We would like to use some "well accepted" methods of finding core subgroups within this meshed network, but I have to confess, while I have done tons of data mining, I've never really done "Social Network Analysis" in a graph-theory type way. I have many years experience analyzing primarily the structure of computer networks, malware, and botnets, and the criminals who run them, but this data set is far beyond my experience and I feel I need more proven tools and techniques to address it properly. My old techniques seem to run out when I get much above 100,000 connections.
Any suggestions on good "getting started" books, articles, or papers would be most helpful.
I've loaded a subset of this data into Pajek ... it represents 8913 social media accounts with 3.9 million connections between them, but realize that I need some theoretical background in Social Network Analysis to really even understand the range of "What might I do next" possibilities.
My objective is to be able to find "strongly connected" and "weakly connected" members, and to determine if there is a connectivity threshold where the network would "split" into two or more clusters.
I would be grateful to the group for any suggested reading. Not afraid to read! I think I need a bit of basic theory before jumping in to the Pajek manual though.
As Thomas Jefferson wrote in 1769 to Thomas Turpin Shadwell: "the only help a youth wants is to be directed what books to read, and in what order to read them."
That's the main help I'm asking for right now. The answer may well be RTFM (Read The Fine Manual), but the question is which M to F'ing R first?
Thanks for any opinions, and I apologize if I've just stumbled across a list FAQ question. A pointer to same would be appreciated if that is the right way to get started!
----------------------------------------------------------
Gary Warner
Director of Research in Computer Forensics
The University of Alabama at Birmingham
Center for Information Assurance and Joint Forensics Research
[log in to unmask]
-----------------------------------------------------------
_____________________________________________________________________
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.
|
