***** To join INSNA, visit http://www.insna.org ***** Great comments and suggestions thus far! Also relevant to this discussion is a book chapter that Caroline Haythornthwaite and I have recently published that deals with issues around social network discovery from textual data on the Internet: * Gruzd, A. & Haythornthwaite, C. (2011). Networking Online: Cyber?ommunities. In Scott, J. & Carrington, P. (Eds.), Handbook of Social Network Analysis. London: Sage, pp. 449-487. Also we've been experimenting with what we call 'Name Networks' - a network discovery method based on examining the content of each message to identify any personal names (and/or usernames) to connect people based on the 'Who-Mentions-Whom' or 'Who-is-CoMentioned-With-Whom' principle. Discovered personal names have shown to be good indicators of the actual addressee(s) of the message as well as good indicators of closer social connections among network members. Here are some papers that relied on this method to study online communities: * Gruzd, A., and Sedo, D.R. (2012) #1b1t: Investigating Reading Practices at the Turn of the Twenty-first Century. Journal of Studies in Book Culture, Special issue on New Studies in the History of Reading, 3(2). doi: 10.7202/1009347ar http://www.erudit.org/revue/memoires/2012/v3/n2/1009347ar.html?vue=integral * Gruzd, A., Wellman, B., and Takhteyev, Y. (2011). Imagining Twitter as an Imagined Community. American Behavioral Scientist, Special issue on Imagined Communities, 55 (10), 1294-1318, doi: 10.1177/0002764211409378 http://abs.sagepub.com/content/55/10/1294 * Haythornthwaite, C. & Gruzd, A. (2008). Analyzing Networked Learning Texts. Proceedings of Networked Learning Conference, Halkidiki, Greece, May 5-6, 2008, pp. 136-143. http://dalspace.library.dal.ca/handle/10222/12828 * Gruzd, A. (2009). Studying Collaborative Learning Using Name Networks. Journal of Education for Library and Information Science, 50(4), 243-253. (Email me to request a copy) FYI.. if you are studying online communities, check out Netlytic (http://netlytic.org/); it's a web-based tool that we've been developing here at the Dalhousie Social Media Lab, designed for both text and network analysis of conversational data. Hope it helps, Anatoliy -- Anatoliy Gruzd, PhD Assistant Professor, School of Information Management Director, Social Media Lab Faculty of Management / Faculty of Computer Science Dalhousie University Canada Phone: 902-494-6119 Fax: 902-494-2451 E-mail: [log in to unmask] Research Lab: http://SocialMediaLab.ca Homepage: http://AnatoliyGruzd.com Twitter: http://twitter.com/dalprof On 06/11/2012 2:09 PM, Maksim Tsvetovat wrote: > ***** To join INSNA, visit http://www.insna.org ***** I've run a fair > bit of analyses commercially where we use SNA to map and analyze the > *concept space* of social media. > > A few lessons learned: > * Because Tweets are so short, it makes little sense to analyze them > in isolation -- larger aggregates work best > > * Concept maps can be used to see in-group and out-group relationships > -- e.g. how do conservatives refer to liberals and liberals to > conservatives? For this analysis, it helps to drop high-degree > concepts (e.g. "liberal", "conservative") -- so commonalities and > differences stand out > > * After dropping high-degree nodes, concept maps can be clustered > using any community detection algorithm. > > * Then, go back to users that have tweeted these concepts, and see > what *other* concepts they tweet about. > > * This forms the basis of an iterative approach -- a sequence of > expansions and contractions of the dataset that gets you very close to > the range of concepts, topics and people that you're looking for. > > * Finally -- if you're analyzing celebrities or politicians (or anyone > with lots of direct speech), concept maps can be used to find > legitimators (e.g. concepts used to establish one's place in the > community) and differentiation markers (e.g. concepts used to make > oneself stand out). > > If you search for me on YouTube, you will find several video lectures > where I use this approach to mine election-related tweets and tweets > about the revolution in Egypt. > > A detailed paper on this technique is in the works and will be > submitted to Social Networks soon. > > Max > > > > On Tue, Nov 6, 2012 at 9:11 AM, Thomas Plotkowiak <[log in to unmask] > <mailto:[log in to unmask]>> wrote: > > ***** To join INSNA, visit http://www.insna.org ***** > I've tried to connect people listed for certain topics such as > "musician" or "snowboard" into a twitter ontology of interests here: > > http://twitterresearcher.wordpress.com/2012/03/16/a-net-of-words-a-high-level-ontology-for-twitter-tags/ > http://twitterresearcher.wordpress.com/2012/06/08/how-to-generate-interest-based-communities-part-1/ > http://twitterresearcher.wordpress.com/2012/06/12/how-to-generate-interest-based-communities-part-2/ > > and thought that it might have a nice application for marketing > when a company wants to know what their followers are itnerested > in, without actually using some sort of text analysis on their > tweets, but instead using their follower ties in this ontology. > > http://twitterresearcher.wordpress.com/2012/07/26/finding-out-what-people-are-interested-in-by-using-only-structural-information/ > > Cheers > Thomas Plotkowiak > Researcher at the MCM Institute St. Gallen > > > > 2012/11/6 patrick doreian <[log in to unmask] <mailto:[log in to unmask]>> > > ***** To join INSNA, visit http://www.insna.org ***** > On 11/6/2012 8:10 AM, Joshua Introne wrote: >> ***** To join INSNA, visit http://www.insna.org ***** >> Hi Derek - >> >> From a somewhat different angle, I've been using Palla's >> (2007) community evolution algorithm to perform evolutionary >> topic analysis in teams. This is intended as a precursor to >> comparative analysis with social network dynamics. >> >> A version of our recently accepted CSCW publication on the >> approach is here: >> http://www.academia.edu/2037735/Analyzing_the_Flow_of_Knowledge_in_Computer_Mediated_Teams. >> >> Best, >> Josh >> >> Joshua Introne, Ph.D >> Research Scientist >> Center for Collective Intelligence >> Sloan School of Management >> Massachusetts Institute of Technology >> >> message. > hi josh, > the paper looks very interesting. but the link > requires access through facebook in order to download it. i do > not, and will not join, facebook for privacy reasons. there > might be others like me so it would nice if you could send a > link that permits real access outside facebook. printing from > the link is impossible. > with best wishes > pat > > > -- > patrick doreian > professor emeritus > department of sociology > 2602 WWPH > university of pittsburgh > pittsburgh, PA 15260 > phone:412 648 7537 <tel:412%20648%207537> > fax:412 648 2799 <tel:412%20648%202799> > website:http://patrickdoreian.com > Social Networks > http://ees.elsevier.com/son/default.asp > > _____________________________________________________________________ > 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] > <mailto:[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] > <mailto:[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. _____________________________________________________________________ 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.