• Save
Automated Discovery and Visualization of Communication Networks from Social Media
Upcoming SlideShare
Loading in...5
×
 

Automated Discovery and Visualization of Communication Networks from Social Media

on

  • 611 views

Presentation given at the London School of Economics, UK

Presentation given at the London School of Economics, UK
(February 20, 2014)

Statistics

Views

Total Views
611
Views on SlideShare
608
Embed Views
3

Actions

Likes
1
Downloads
0
Comments
0

1 Embed 3

https://twitter.com 3

Accessibility

Categories

Upload Details

Uploaded via as Microsoft PowerPoint

Usage Rights

© All Rights Reserved

Report content

Flagged as inappropriate Flag as inappropriate
Flag as inappropriate

Select your reason for flagging this presentation as inappropriate.

Cancel
  • Full Name Full Name Comment goes here.
    Are you sure you want to
    Your message goes here
    Processing…
Post Comment
Edit your comment
  • Dataset Name ukraineDataset Last Updated on 2014-02-19 18:59:11Dataset Source Dataset source was uploaded by a userTotal Messages 24000Unique Posters 17423Report Created on February 19, 2014, 7:22 pm
  • General Info  Value Dataset Name #УкраїнаDataset Last Updated on 2014-02-19 19:59:11Dataset Source Dataset source was uploaded by a userTotal Messages 6496Unique Posters 3962Report Created on February 19, 2014, 8:03 pm

Automated Discovery and Visualization of Communication Networks from Social Media Automated Discovery and Visualization of Communication Networks from Social Media Presentation Transcript

  • Automated Discovery and Visualization of Communication Networks from Social Media Anatoliy Gruzd @gruzd gruzd@dal.ca Associate Professor, School of Information Management Director, Social Media Lab Faculty of Management / Faculty of Computer Science Dalhousie University London School of Economics February 20, 2014
  • Outline • Studying Online Social Networks • Sample Projects • Netlytic.org Anatoliy Gruzd Twitter: @gruzd 2
  • Growth of Social Media and Social Networks Data Facebook Social Media have become an integral part of our daily lives! Twitter 1B users 500M users
  • How to Make Sense of Social Big Data? Anatoliy Gruzd Twitter: @gruzd 10
  • How to Make Sense of Social Big Data? Social Big Data -> Visualizations -> Understanding (Development, Application & Validation) Anatoliy Gruzd Twitter: @gruzd 11
  • How to Make Sense of Social Big Data? Social Network Analysis (SNA) • Nodes = People • Edges /Ties (lines) = Relations/ “Who retweeted/ replied/ mentioned whom” Anatoliy Gruzd Twitter: @gruzd 12
  • Advantages of Social Network Analysis • Reduce the large quantity of data into a more concise representation • Makes it much easier to understand what is going on in a group Anatoliy Gruzd Once the network is discovered, we can find out: • How do people interact with each other, • Who are the most/least active members of a group, • Who is influential in a group, • Who is susceptible to being influenced, etc… Twitter: @gruzd 13
  • How Do We Collect Information About Online Social Networks? Common approach for collecting social network data: • Self-reported social network data may not be available/accurate • Surveys or interviews Problems with surveys or interviews • • • • • Time-consuming Questions can be too sensitive Answers are subjective or incomplete Participant can forget people and interactions Different people perceive events and relationships differently Anatoliy Gruzd Twitter: @gruzd 14
  • How Do We Collect Information About Social Networks? • Common approach: surveys or interviews • A sample question about students’ perceived social structures Please indicate on a scale from [1] to [5], YOUR FRIENDSHIP RELATIONSHIP WITH EACH STUDENT IN THE CLASS [1] - don’t know this person [2] - just another member of class [3] - a slight friendship [4] - a friend [5] - a close friend Alice D. [1] [2] [3] [4] [5] … Richard S. [1] [2] [3] [4] [5] Source: C. Haythornthwaite, 1999 Anatoliy Gruzd Twitter: @gruzd 15
  • How Do We Collect Information About Online Social Networks? Goal: Automated Networks Discovery Challenge: Figuring out what content-based features of online interactions can help to uncover nodes and ties between group members Anatoliy Gruzd Twitter: @gruzd 16
  • How Do We Collect Information About Online Social Networks? • Forum networks • Blog networks • Friends’ networks (Facebook, Twitter, Google+, etc…) • Networks of like-minded people (YouTube, Flickr, etc…) http://www.visualcomplexity.com/vc
  • Automated Discovery of Social Networks Direct Facebook Messages • Nodes = People Nick • Ties = “Who talks to whom” Rick • Tie strength = The number of messages exchanged between individuals Dick Anatoliy Gruzd Twitter: @gruzd 18
  • Automated Discovery of Social Networks “Many to Many” Communication Forum Anatoliy Gruzd Mailing listserv Chat Twitter: @gruzd Comments 19
  • Automated Discovery of Social Networks Approach 1: Chain Network (Reply-to) Posting header FROM: Sam PREVIOUS POSTER: Gabriel Content .... .... .... Anatoliy Gruzd Twitter: @gruzd 20
  • Automated Discovery of Social Networks Approach 1: Chain Network (Reply-to) Posting header FROM: Sam PREVIOUS POSTER: Gabriel Content “ Nick, Gina and Gabriel: I apologize for not backing this up with a good source, but I know from reading about this topic that … ” Possible Missing Connections: • Sam -> Nick • Sam -> Gina • Nick <-> Gina
  • Automated Discovery of Social Networks Approach 2: Name Network This approach looks for personal names in the content of the messages to identify social connections between group members. FROM: Ann “Steve and Natasha, I couldn't wait to see your site. I knew it was going to [be] awesome!” Anatoliy Gruzd Twitter: @gruzd 22
  • Automated Discovery of Social Networks Approach 2: Name Network • Main Communicative Functions of Personal Names (Leech, 1999) – getting attention and identifying addressee – maintaining and reinforcing social relationships • Names are “one of the few textual carriers of identity” in discussions on the web (Doherty, 2004) • Their use is crucial for the creation and maintenance of a sense of community (Ubon, 2005) • Remembering a person’s name can potentially shape that person’s response to a request (Howard et al. 1995, 1997) Anatoliy Gruzd Twitter: @gruzd 23
  • Automated Discovery of Social Networks Name Network Method: Challenges Kurt Cobain, a lead singer for the rock band Nirvana chris is not a group member Santa Monica Public Library John Dewey, philosopher & educator mark up language Solution: - Name alias resolution Anatoliy Gruzd Twitter: @gruzd 24
  • Evaluating Name Networks Example: Youtube comments Name Network Chain Network Chain Network (less connections) Anatoliy Gruzd Name Network (more connections) Twitter: @gruzd 25
  • Automated Discovery of Social Networks Twitter Messages • Nodes = People @John • Ties = “Who retweeted/ replied/mentioned whom” • Tie strength = The number of retweets, replies or mentions @Peter @Paul Anatoliy Gruzd Twitter: @gruzd 26
  • 2012 Olympics in London Twitter: @dalprof Anatoliy Gruzd
  • #tarsand Twitter Community Twitter: @dalprof Anatoliy Gruzd
  • #1b1t Twitter Book Club Twitter: @dalprof Anatoliy Gruzd
  • Outline • Studying Online Social Networks • Sample Projects (1) Politics & (2) Health • Netlytic.org Anatoliy Gruzd Twitter: @gruzd 30
  • Sample Project: Politics Political Polarization on Social Media Gruzd, A. and Roy, J (2014, forthcoming). Political Polarization on Social Media: Do Birds of a Feather Flock Together on Twitter? Policy & Internet.
  • Sample Project: Politics Social Media Use during the Canadian Federal Election #CndPoli Twitter Communication Network (April 6-9, 2011) Anatoliy Gruzd Twitter: @gruzd 32
  • Sample Project: Politics Social Media Use during the Canadian Federal Election • There are some pockets of political polarization on Twitter Conservative – homophily - when people in social networks tend to group around similar backgrounds and interests, including shared political views. Left Liberal • Twitter has potential for supporting open cross-ideological discourse Anatoliy Gruzd Unknown & Undecided Green Bloc – 43% of the accounts in the sample did not explicitly stated their support for any party or stated support to more than one party Spam NDP Other Manual Classification of Twitter Users based on their self-declared party affiliation Twitter: @gruzd 33
  • Sample Project: Health Social Media & Health Gruzd, A. & Haythornthwaite, C. (2013). Enabling Community through Social Media. Journal of Medical Internet Research 15(10):e248. DOI: 10.2196/jmir.2796
  • Sample Project: Health Health Care Social Media Canada Case Study: #hcsmca Twitter Community Background • #hcsmca is a vibrant community of people interested in exploring social innovation in health care. • #hcsmca hosts a tweet chat every Wednesday at 1 pm ET. The last Wednesday of the month is our monthly evening chat at 9 pm ET. Source: http://cyhealthcommunications.wordpress.com/hcsmca-2/ Anatoliy Gruzd Twitter: @gruzd 35
  • Sample Project: Health Health Care Social Media Canada Case Study: #hcsmca Twitter Community Research question: 1. What accounts for the relative longevity of this particular online community? – Is it because of the founder’s leadership and her continuing involvement in this community? – Or is there a core group of members who are also actively and persistently involved in this community? 2. What is the composition of this community? Does one’s professional role/title determine a person’s centrality within this community. Anatoliy Gruzd Twitter: @gruzd 36
  • Sample Project: Health Some Topics Discussed by the #hcsmca Community Nov 14, 2012 Challenge of engaging SM to inform a research agenda Nov 21, 2012 Are healthcare blogs a useful tool for education and knowledge transfer? Number of Messages Over Time Anatoliy Gruzd Twitter: @gruzd 37
  • Sample Project: Health #hcsmca Communication Network on Twitter (Nov 12 - Dec 13, 2012) Roles SM health content providers Unaffiliated individual users Communicators - not specifically health related Communicators - Health related Count Healthcare professionals 50 Health institutions 31 Advocacy 30 Students 16 Educators, professors 13 Researchers Government and health policy makers 10 110 89 74 59 4 *Roles are assigned manually Node size = In-Degree Centrality Anatoliy Gruzd Twitter: @gruzd 38
  • Outline • Studying Online Social Networks • Sample Projects (1) Politics & (2) Health • Netlytic.org Twitter: @gruzd Anatoliy Gruzd 39
  • Netlytic.org - a cloud-based analytic tool Anatoliy Gruzd Networks Content Stats for automated text analysis & discovery of social networks from online communication Twitter: @gruzd 40
  • http://www.theguardian.com/world/2014/feb/18/ukraine-policestorm-kiev-protest-camp-live-updates#start-of-comments
  • Ukraine Feb-19-2014
  • Ukraine Feb-19-2014
  • Ukraine Feb-19-2014