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.
June 20, 2017
Philip Mai
@phmai
Director of Business &
Communications
Anatoliy Gruzd
@gruzd
Canada Research Chair
Associat...
Outline
1. About the
Social Media
Lab
2. Social
Media Data
Collection
3. Intro to
SNA
4. Hands-on
Part
Slides at http://bi...
We are an interdisciplinary academic research laboratory
▪ Online Communities
▪ Social Network Analysis (SNA)
▪ Information Visualization & Dashboard
▪ Text Mining
▪ Distributed C...
At the Social Media LabWe Study…
How can social media
support online
communities, social
activism & political
engagement?
...
At the Social Media LabWe Organize…
International Conferences and Events
SocialMediaAndSociety.org AltmetricsConference.co...
At the Social Media LabWe Develop…
Social Media Analytics Software
@SMLabTO
Anatoliy Gruzd
@SMLabTO
SOCIAL MEDIA RESEARCH TOOLKIT
socialmediadata.org
A Curated List of 50+
Peer Tested & Peer
Reviewe...
Outline
1. About the
Social Media
Lab
2. Social
Media Data
Collection
3. Intro to
SNA
4. Hands-on
Part
@SMLabTO
Slides at ...
Social Media sites have become
an integral part of our daily lives!
GROWTH OF SOCIAL MEDIA DATA
Facebook
1.8B
users
Instag...
Decision Making
in domains such as Business, Education, Politics, Health Care, etc…
HOW TO MAKE SENSE OF SOCIAL MEDIA DATA...
HOW TO MAKE SENSE OF SOCIAL MEDIA DATA?
Big Data Technology
12
Cloud &
Distributed
Computing
Data &
Information
Organizati...
Data -> Visualizations -> Understanding
HOW TO MAKE SENSE OF SOCIAL MEDIA DATA?
@SMLabTO
Nodes = People Edges /Ties (lines) = Relations
“Who retweeted/ replied/ mentioned whom”
HOW TO MAKE SENSE OF SOCIAL MEDIA ...
Makes it much easier to understand what is going on in a group
ADVANTAGES OF SOCIAL NETWORK ANALYSIS
Once the network is d...
Common approach: surveys or interviews and self-reported social network
• A sample question about students’ perceived soci...
Problems with surveys or interviews
• Time-consuming
• Questions can be too sensitive
• Answers are subjective or incomple...
Goal: Automated Networks Discovery
Challenge: Figuring out what content-based features of online interactions can
help to ...
Outline
1. About the
Social Media
Lab
2. Social
Media Data
Collection
3. Intro to
SNA
4. Hands-on
Part
Questions?
@SMLabTO...
@John
@Peter
@Paul • Nodes = People/Accounts
• Ties = “Who retweeted/
replied/mentioned whom”
• Tie strength = The number ...
AUTOMATED DISCOVERY OF SOCIAL NETWORKS
Connection Discovery Examples
Network Ties
@Cheeflo -> @JoeProf
@Cheeflo -> @VMosco...
SAMPLE TWITTER DATASET
SIMPLE SEARCH FOR #HONGKONG
3557 tweets @SMLabTO
#HONGKONG TWITTER NETWORK
What does this visualization
tell us?
3557 tweets
@SMLabTO
SNA MEASURES
Micro-level
In-degree centrality
Out-degree centrality
Betweenness centrality
Other centrality measures (e.g....
SNA MEASURES
Micro-level
In-degree centrality
Out-degree centrality
Betweenness centrality
Other centrality measures (e.g....
IN-DEGREE CENTRALITY
#HONGKONG TWITTER NETWORK
Note: SEVENTEEN or SVT is
a S.Korean boy group formed
by Pledis Entertainme...
SNA MEASURES
Micro-level
In-degree centrality
Out-degree centrality
Betweenness centrality
Other centrality measures (e.g....
OUT-DEGREE CENTRALITY
#HONGKONG TWITTER NETWORK
Note: A music fan (many
retweets & replies to others)
@SMLabTO
SNA MEASURES
Micro-level
In-degree centrality
Out-degree centrality
Betweenness centrality
Other centrality measures (e.g....
BETWEENNESS CENTRALITY
#HONGKONG TWITTER NETWORK
Note: A fan (retweets/replies to
messages from two different fan
communit...
Outline
1. About the
Social Media
Lab
2. Social
Media Data
Collection
3. Intro to
SNA
4. Hands-on
Part
Questions?
@SMLabTO...
Case Study: #ExploreCanada on Twitter by
Destination Canada
Twitter: @gruzd ANATOLIY GRUZD 34
Practice with Netlytic.org
Exploring #ExploreCanada via Social Network Analysis
Tutorial Steps:
https://netlytic.org/home/...
Twitter: @gruzd ANATOLIY GRUZD 36
Live Demo: https://netlytic.org/network/sigma.php?c=YIZ5D21C5m05K2FV&viz=2&datatype=twit...
SNA Measures
Micro-level
In-degree centrality
Out-degree centrality
Betweenness centrality
Other centrality measures (e.g....
Sample Twitter Searches
#ELECTION2016 #HONGKONG
Twitter: @gruzd ANATOLIY GRUZD 38
3557 records1394 records
Sample Twitter Searches
#ELECTION2016 #HONGKONG
Twitter: @gruzd ANATOLIY GRUZD 39
3557 records1394 records
SNA Measures
Macro-level
Density
Diameter
Reciprocity
Centralization
Modularity
Density indicates the overall
connectivity...
#Election2016 #HongKong
Nodes 491 2570
Edges 1075 2447
Density 0.005 (0.5%) 0.0004 (0.04%)
Diameter
Reciprocity
Centraliza...
SNA Measures
Macro-level
Density
Diameter
Reciprocity
Centralization
Modularity
Diameter gives a general idea of how
“wide...
#Election2016 #HongKong
Nodes 491 2570
Edges 1075 2447
Density 0.005 (0.5%) 0.0004 (0.04%)
Diameter 28 14
Reciprocity
Cent...
SNA Measures
Macro-level
Density
Diameter
Reciprocity
Centralization
Modularity
Reciprocity shows how many online
particip...
#Election2016 #HongKong
Nodes 491 2570
Edges 1075 2447
Density 0.005 (0.5%) 0.0004 (0.04%)
Diameter 28 14
Reciprocity 0.00...
SNA Measures
Macro-level
Density
Diameter
Reciprocity
Centralization
Modularity
Centralization indicates whether a network...
#Election2016 #HongKong
Nodes 491 2570
Edges 1075 2447
Density 0.005 (0.5%) 0.0004 (0.04%)
Diameter 28 14
Reciprocity 0.00...
SNA Measures
Macro-level
Density
Diameter
Reciprocity
Centralization
Modularity
Modularity provides an estimate of
whether...
#Election2016 #HongKong
Nodes 491 2570
Edges 1075 2447
Density 0.005 (0.5%) 0.0004 (0.04%)
Diameter 28 14
Reciprocity 0.00...
Twitter: @gruzd ANATOLIY GRUZD 50
Live Demo: https://netlytic.org/network/sigma.php?c=YIZ5D21C5m05K2FV&viz=2&datatype=twit...
#ExploreCanada #Election2016 #HongKong
Nodes 1196 491 2570
Edges 2017 1075 2447
Density 0.0014 (0.14%) 0.005 (0.5%) 0.0004...
Outline
1. About the
Social Media
Lab
2. Social
Media Data
Collection
3. Intro to
SNA
4. Hands-on
Part
@SMLabTO
Slides at ...
June 20, 2017
Philip Mai
@phmai
Director of Business &
Communications
Anatoliy Gruzd
@gruzd
Canada Research Chair
Associat...
Upcoming SlideShare
Loading in …5
×

Social listening: how to do it and how to use (SNA Perspective)

420 views

Published on

Anatoliy Gruzd and Philip Mai
Workshop presented at the TTRA Annual International Conference in Quebec City (June 20, 2017)

https://2017ttraannualinternationalconfe.sched.com/event/9yCg/social-listening-how-to-do-it-and-how-to-use-it-veille-sociale-comment-faire-et-comment-lutiliser?iframe=no&w=100%&sidebar=no&bg=no

Published in: Education
  • Be the first to comment

Social listening: how to do it and how to use (SNA Perspective)

  1. 1. June 20, 2017 Philip Mai @phmai Director of Business & Communications Anatoliy Gruzd @gruzd Canada Research Chair Associate Professor Director of Research @SMLabTO Social Listening: How To Do It and How To Use It Veille sociale: comment faire et comment l'utiliser Social Media Lab Ted Rogers School of Management, Ryerson University
  2. 2. Outline 1. About the Social Media Lab 2. Social Media Data Collection 3. Intro to SNA 4. Hands-on Part Slides at http://bit.ly/ttra-sna
  3. 3. We are an interdisciplinary academic research laboratory
  4. 4. ▪ Online Communities ▪ Social Network Analysis (SNA) ▪ Information Visualization & Dashboard ▪ Text Mining ▪ Distributed Computing ▪ Computer Mediated Communication ▪ Director of Research ▪ Director of Business & Communications ▪ Post Docs, Project Manager, PhD Students, Master and Undergraduate students ▪ Faculty Research Collaborators across Canada and abroad (USA, UK, Russia, Brazil, HK, S. Korea) @SMLabTO Our ExpertiseOur Team
  5. 5. At the Social Media LabWe Study… How can social media support online communities, social activism & political engagement? What does it mean to be “influential” online? How can social media help to enhance teaching & learning in higher education? Is happiness/swearing contagious online? What predicts user engagement on social media? Is information privacy dead in the social media age? @SMLabTOSocialMediaData.org @SMLabTO
  6. 6. At the Social Media LabWe Organize… International Conferences and Events SocialMediaAndSociety.org AltmetricsConference.com @SMLabTO
  7. 7. At the Social Media LabWe Develop… Social Media Analytics Software @SMLabTO
  8. 8. Anatoliy Gruzd @SMLabTO SOCIAL MEDIA RESEARCH TOOLKIT socialmediadata.org A Curated List of 50+ Peer Tested & Peer Reviewed Social Media Research Tools. No Coding Required (OK…maybe some coding req.)
  9. 9. Outline 1. About the Social Media Lab 2. Social Media Data Collection 3. Intro to SNA 4. Hands-on Part @SMLabTO Slides at http://bit.ly/ttra-sna
  10. 10. Social Media sites have become an integral part of our daily lives! GROWTH OF SOCIAL MEDIA DATA Facebook 1.8B users Instagram 600M users Twitter 300M users @SMLabTO
  11. 11. Decision Making in domains such as Business, Education, Politics, Health Care, etc… HOW TO MAKE SENSE OF SOCIAL MEDIA DATA? Self- collected /reported Public APIs Data Resellers @SMLabTO
  12. 12. HOW TO MAKE SENSE OF SOCIAL MEDIA DATA? Big Data Technology 12 Cloud & Distributed Computing Data & Information Organization Analytics Visualization @SMLabTO
  13. 13. Data -> Visualizations -> Understanding HOW TO MAKE SENSE OF SOCIAL MEDIA DATA? @SMLabTO
  14. 14. Nodes = People Edges /Ties (lines) = Relations “Who retweeted/ replied/ mentioned whom” HOW TO MAKE SENSE OF SOCIAL MEDIA DATA? Social Network Analysis (SNA) @SMLabTO
  15. 15. Makes it much easier to understand what is going on in a group ADVANTAGES OF SOCIAL NETWORK ANALYSIS Once the network is discovered, we can find out: • How do people interact with each other? • Who are influential users in a group? • Who are susceptible to being influenced? • Who is a human and who is a bot? • … Liberal Conservative Spam Unknown & Undecided NDP Left Green Bloc Other Gruzd, A. and Roy, J (2014). Political Polarization on Social Media: Do Birds of a Feather Flock Together on Twitter? Policy & Internet. @SMLabTO
  16. 16. Common approach: surveys or interviews and self-reported social network • A sample question about students’ perceived social structures HOW DO WE COLLECT INFORMATION ABOUT SOCIAL NETWORKS? 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 @SMLabTO
  17. 17. 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 HOW DO WE COLLECT INFORMATION ABOUT SOCIAL NETWORKS? @SMLabTO
  18. 18. Goal: Automated Networks Discovery Challenge: Figuring out what content-based features of online interactions can help to uncover nodes and ties between group members HOW DO WE COLLECT INFORMATION ABOUT ONLINE SOCIAL NETWORKS? @SMLabTO
  19. 19. Outline 1. About the Social Media Lab 2. Social Media Data Collection 3. Intro to SNA 4. Hands-on Part Questions? @SMLabTO Slides at http://bit.ly/ttra-sna
  20. 20. @John @Peter @Paul • Nodes = People/Accounts • Ties = “Who retweeted/ replied/mentioned whom” • Tie strength = The number of retweets, replies or mentions AUTOMATED DISCOVERY OF SOCIAL NETWORKS Twitter Networks @SMLabTO
  21. 21. AUTOMATED DISCOVERY OF SOCIAL NETWORKS Connection Discovery Examples Network Ties @Cheeflo -> @JoeProf @Cheeflo -> @VMosco @JoeProf -> @VMosco Network Tie @Gruzd -> @SidneyEve Connection type: Mention Connection type: Reply @SMLabTO
  22. 22. SAMPLE TWITTER DATASET SIMPLE SEARCH FOR #HONGKONG 3557 tweets @SMLabTO
  23. 23. #HONGKONG TWITTER NETWORK What does this visualization tell us? 3557 tweets @SMLabTO
  24. 24. SNA MEASURES Micro-level In-degree centrality Out-degree centrality Betweenness centrality Other centrality measures (e.g., closeness, eigenvector) Macro-level Density Diameter Reciprocity Centralization Modularity @SMLabTO
  25. 25. SNA MEASURES Micro-level In-degree centrality Out-degree centrality Betweenness centrality Other centrality measures (e.g., closeness, eigenvector)  In-degree suggests “prestige” highlighting the most mentioned or replied Twitter users @SMLabTO
  26. 26. IN-DEGREE CENTRALITY #HONGKONG TWITTER NETWORK Note: SEVENTEEN or SVT is a S.Korean boy group formed by Pledis Entertainment @SMLabTO
  27. 27. SNA MEASURES Micro-level In-degree centrality Out-degree centrality Betweenness centrality Other centrality measures (e.g., closeness, eigenvector)  Out-degree reveals active Twitter users with a good awareness of others in the network @SMLabTO
  28. 28. OUT-DEGREE CENTRALITY #HONGKONG TWITTER NETWORK Note: A music fan (many retweets & replies to others) @SMLabTO
  29. 29. SNA MEASURES Micro-level In-degree centrality Out-degree centrality Betweenness centrality Other centrality measures (e.g., closeness, eigenvector) Anatoliy Gruzd  Betweenness shows actors who are located on the most number of information paths and who often connect different groups of users in the network Twitter: @gruzd @SMLabTO
  30. 30. BETWEENNESS CENTRALITY #HONGKONG TWITTER NETWORK Note: A fan (retweets/replies to messages from two different fan communities/sites) @SMLabTO
  31. 31. Outline 1. About the Social Media Lab 2. Social Media Data Collection 3. Intro to SNA 4. Hands-on Part Questions? @SMLabTO Slides at http://bit.ly/ttra-sna
  32. 32. Case Study: #ExploreCanada on Twitter by Destination Canada Twitter: @gruzd ANATOLIY GRUZD 34
  33. 33. Practice with Netlytic.org Exploring #ExploreCanada via Social Network Analysis Tutorial Steps: https://netlytic.org/home/?p=11510 Also see Gruzd, A., Paulin, D., & Haythornthwaite, C. (2016). Analyzing Social Media and Learning Through Content and Social Network Analysis: A Faceted Methodological Approach. Journal of Learning Analytics 3(3). Available at https://eric.ed.gov/?id=EJ1126777 Twitter: @gruzd ANATOLIY GRUZD 35
  34. 34. Twitter: @gruzd ANATOLIY GRUZD 36 Live Demo: https://netlytic.org/network/sigma.php?c=YIZ5D21C5m05K2FV&viz=2&datatype=twitter
  35. 35. SNA Measures Micro-level In-degree centrality Out-degree centrality Betweenness centrality Other centrality measures (e.g., closeness, eigenvector) Macro-level Density Diameter Reciprocity Centralization Modularity ANATOLIY GRUZD 37@gruzd
  36. 36. Sample Twitter Searches #ELECTION2016 #HONGKONG Twitter: @gruzd ANATOLIY GRUZD 38 3557 records1394 records
  37. 37. Sample Twitter Searches #ELECTION2016 #HONGKONG Twitter: @gruzd ANATOLIY GRUZD 39 3557 records1394 records
  38. 38. SNA Measures Macro-level Density Diameter Reciprocity Centralization Modularity Density indicates the overall connectivity in the network (the total number of connections divided by the total number of possible connections). It is equal to 1 when everyone is connected to everyone. ANATOLIY GRUZD 40Twitter: @gruzd User1 User3 User2 Density = 1
  39. 39. #Election2016 #HongKong Nodes 491 2570 Edges 1075 2447 Density 0.005 (0.5%) 0.0004 (0.04%) Diameter Reciprocity Centralization Modularity ANATOLIY GRUZD 41Twitter: @gruzd
  40. 40. SNA Measures Macro-level Density Diameter Reciprocity Centralization Modularity Diameter gives a general idea of how “wide” the network is; the longest of the shortest paths between any two nodes in the network. ANATOLIY GRUZD 42Twitter: @gruzd #1 User1 User3 User2 User4 Diameter = 3 #2 #3
  41. 41. #Election2016 #HongKong Nodes 491 2570 Edges 1075 2447 Density 0.005 (0.5%) 0.0004 (0.04%) Diameter 28 14 Reciprocity Centralization Modularity ANATOLIY GRUZD 43Twitter: @gruzd
  42. 42. SNA Measures Macro-level Density Diameter Reciprocity Centralization Modularity Reciprocity shows how many online participants are having two-way conversations. In a scenario when everyone replies to everyone, the reciprocity value will be 1. ANATOLIY GRUZD 44Twitter: @gruzd User2 User1 User3 User4 Reciprocity=1
  43. 43. #Election2016 #HongKong Nodes 491 2570 Edges 1075 2447 Density 0.005 (0.5%) 0.0004 (0.04%) Diameter 28 14 Reciprocity 0.006 (0.6%) 0.003 (0.3%) Centralization Modularity ANATOLIY GRUZD 45Twitter: @gruzd
  44. 44. SNA Measures Macro-level Density Diameter Reciprocity Centralization Modularity Centralization indicates whether a network is dominated by few central participants (values are closer to 1), or whether more people are contributing to discussion and information dissemination (values are closer to 0). ANATOLIY GRUZD 46Twitter: @gruzd User2 User1User3 User4 Centralization=1
  45. 45. #Election2016 #HongKong Nodes 491 2570 Edges 1075 2447 Density 0.005 (0.5%) 0.0004 (0.04%) Diameter 28 14 Reciprocity 0.006 (0.6%) 0.003 (0.3%) Centralization 0.05 0.11 Modularity ANATOLIY GRUZD 47Twitter: @gruzd
  46. 46. SNA Measures Macro-level Density Diameter Reciprocity Centralization Modularity Modularity provides an estimate of whether a network consists of one coherent group of participants who are engaged in the same conversation and who are paying attention to each other (values closer to 0); or whether a network consists of different conversations and communities with a weak overlap (values closer to 1). ANATOLIY GRUZD 48Twitter: @gruzd
  47. 47. #Election2016 #HongKong Nodes 491 2570 Edges 1075 2447 Density 0.005 (0.5%) 0.0004 (0.04%) Diameter 28 14 Reciprocity 0.006 (0.6%) 0.003 (0.3%) Centralization 0.05 0.11 Modularity 0.42 0.92 ANATOLIY GRUZD 49Twitter: @gruzd
  48. 48. Twitter: @gruzd ANATOLIY GRUZD 50 Live Demo: https://netlytic.org/network/sigma.php?c=YIZ5D21C5m05K2FV&viz=2&datatype=twitter Hands-On Part Macro-level SNA Measures in Netlytic
  49. 49. #ExploreCanada #Election2016 #HongKong Nodes 1196 491 2570 Edges 2017 1075 2447 Density 0.0014 (0.14%) 0.005 (0.5%) 0.0004 (0.04%) Diameter 18 28 14 Reciprocity 0.0188 (1.9%) 0.006 (0.6%) 0.003 (0.3%) Centralization 0.13 0.05 0.11 Modularity 0.70 0.42 0.92 ANATOLIY GRUZD 51@gruzd
  50. 50. Outline 1. About the Social Media Lab 2. Social Media Data Collection 3. Intro to SNA 4. Hands-on Part @SMLabTO Slides at http://bit.ly/ttra-sna
  51. 51. June 20, 2017 Philip Mai @phmai Director of Business & Communications Anatoliy Gruzd @gruzd Canada Research Chair Associate Professor Director of Research @SMLabTO Social Listening: How To Do It and How To Use It Veille sociale: comment faire et comment l'utiliser Social Media Lab Ted Rogers School of Management, Ryerson University

×