Successfully reported this slideshow.
We use your LinkedIn profile and activity data to personalize ads and to show you more relevant ads. You can change your ad preferences anytime.

The Basics of Social Network Analysis


Published on

An introduction in the world of Social Network Analysis and a view on how this may help learning networks. History, data collection and several analysis techniques are shown.

Published in: Education, Technology
  • Login to see the comments

The Basics of Social Network Analysis

  1. 1. The Basics of Social Network Analysis <ul><li>Adriana Berlanga & Rory Sie </li></ul><ul><li>LN SNA Seminar series, November 15th 2011 </li></ul>
  2. 2. Outline <ul><li>History </li></ul><ul><li>Examples </li></ul><ul><li>Network Data </li></ul><ul><li>Analysis </li></ul>
  3. 3. History Social Network Analysis Psychology Anthropology
  4. 4. 1930s: Jacob Moreno sociogram
  5. 5. 1950s: Cartwright and Harary Dorwin Cartwright Frank Harary + - - A B C “ any balanced graph can be divided into two cohesive sub-groups that are in conflict with each other”
  6. 6. 1920s: Warner and Mayo Mayo Warner Hawthorne effect focus on relationships
  7. 7. 1920s: Warner and Mayo Mayo Warner adapted from Scott, 2000 cliques every person is separated by only one step
  8. 8. Social Networks <ul><li>1950s: ‘network’ (Barnes, Bott, Nadel) </li></ul><ul><li>1960s: Density and reachability (Mitchell) </li></ul>A B C D E A-B-C-E
  9. 9. Mark Granovetter <ul><li>Getting a Job (1974) </li></ul><ul><li>Strength of weak ties (1983) </li></ul>://
  10. 10. History Social Network Analysis Psychology Anthropology Hawthorne Networks Graph theory Sociogram Graph theory Strength of weak ties
  11. 11. Examples centrality = power (Krackhardt, 1990) ‘ broker’ (Burt, 2004)
  12. 12. Why? <ul><li>encourages re-use and prevent re-invention </li></ul><ul><li>increase knowledge sharing </li></ul><ul><li>discover effective and efficient (sub)communities </li></ul><ul><li>reduce burden on experts/teachers </li></ul>adapted from Liebowitz, 2005
  13. 13. Data collection
  14. 14. Ego network ego network but.... self-perceived ask for connections ask connections if they are connected alter alter
  15. 15. Snowball method but.... self-perceived ask for connections ask connections for their connections until you reach a stopping criterion
  16. 16. Complete networks monitor email traffic or monitor tweets
  17. 17. Data storage Adjacency matrix (R, UCINET)
  18. 18. Data storage <ul><li><?xml version=&quot;1.0&quot; encoding=&quot;UTF-8&quot; standalone=&quot;yes&quot;?><graph label=&quot;PLN for ID &quot; directed=&quot;1&quot;> </li></ul><ul><li><node id=&quot; n26 &quot; label=&quot;n26&quot;><att type=&quot;string&quot; name=&quot;PeerName&quot; value=&quot; Rory Sie &quot;/></node><node id=&quot; n27 &quot; label=&quot;n27&quot;><att type=&quot;string&quot; name=&quot;PeerName&quot; value=&quot; Adriana Berlanga &quot;/></node><edge id=&quot;e0&quot; label=&quot;e0&quot; source=&quot; n26 &quot; target=&quot; n27 &quot;><att type=&quot;string&quot; name=&quot;interaction&quot; value=&quot;colleague&quot;&quot;/> </li></ul><ul><ul><li></edge> </li></ul></ul><ul><ul><ul><li></graph> </li></ul></ul></ul>GML/ XGMML (Cytoscape, Gephi)
  19. 19. Data storage Pajek network (Pajek, UCINET)
  20. 20. Analysis: network <ul><li>Density </li></ul><ul><li>Connectivity k </li></ul><ul><li>Centralization </li></ul>A D C B E
  21. 21. Analysis: community <ul><li>Clique </li></ul>A D C B E F every person in a clique can be reached within 1 step
  22. 22. Analysis: community <ul><li>N-clique </li></ul>A D C B E F every person can be reached within n steps. ABCF is a 2-clique
  23. 23. Analysis: community A D C B E F Faction
  24. 24. Analysis: individual A D C B E F G H Betweenness network is dependent on C Degree G is very popular 12 12 14 17 17 18 19 19 Closeness C and G can easily reach others
  25. 25. Summary <ul><li>Why? </li></ul><ul><ul><li>encourages re-use </li></ul></ul><ul><ul><li>reduce burden on teacher </li></ul></ul><ul><ul><li>discover effective and efficient (sub)communities </li></ul></ul><ul><li>Data collection </li></ul><ul><li>Which technique? </li></ul>
  26. 26. References <ul><li>Brandes, U. (1994). A Faster Algorithm for Betweenness Centrality. Journal of Mathematical Sociology , 25 (2), 163-177. </li></ul><ul><li>Burt, R. S. (2004). Structural Holes and Good Ideas. American Journal of Sociology , 110 (2), 349-399. doi:10.1086/421787 </li></ul><ul><li>Cartwright, D., & Harary, F. (1977). A Graph Theoretic Approach to the Investigation of System-Environment Relationships. Journal of Mathematical Sociology , 5 , 87-111. </li></ul><ul><li>Granovetter, M. (1974). Getting A Job: A Study of Contacts and Careers. Cambridge, Massachusetts. </li></ul><ul><li>Krackhardt, D. (1990). Assessing the Political Landscape : Structure, Cognition, and Power in Organizations. Administrative Science Quarterly , 35 (2), 342-369. </li></ul><ul><li>Liebowitz, J. (2005). Linking social network analysis with the analytic hierarchy process for knowledge mapping in organizations. Journal of Knowledge Management , 9 (1), 76-86. doi:10.1108/13673270510582974 </li></ul><ul><li>Scott, J. (2000). Social Network Analysis: a Handbook (p. 208). SAGE Publications, Inc. </li></ul><ul><li>Factions video. </li></ul>
  27. 27. Questions? <ul><li>[email_address] </li></ul><ul><li> </li></ul><ul><li>openrory, maisonpoublon </li></ul><ul><li>Rory Sie </li></ul><ul><li>openrse </li></ul><ul><li> </li></ul><ul><li> </li></ul>
  28. 28. NOW: PLN Drawing <ul><li> </li></ul><ul><ul><li>register </li></ul></ul><ul><ul><li>add the people you learn from! </li></ul></ul><ul><ul><li>15 minutes </li></ul></ul>