eventgraphs talk at hcil2011
DESCRIPTION
This talk discusses and illustrates EventGraphs, a genre of social network diagram that illustrate the social structure of mass conversations around events.TRANSCRIPT
![Page 1: EventGraphs Talk at HCIL2011](https://reader035.vdocuments.net/reader035/viewer/2022062513/554d8a2fb4c9053e0c8b5484/html5/thumbnails/1.jpg)
EventGraphs: mapping the social structure of events with NodeXL
![Page 2: EventGraphs Talk at HCIL2011](https://reader035.vdocuments.net/reader035/viewer/2022062513/554d8a2fb4c9053e0c8b5484/html5/thumbnails/2.jpg)
Mass Conversations of Events
Research Goal: Augment people’s ability to make sense of mass conversations of events
![Page 3: EventGraphs Talk at HCIL2011](https://reader035.vdocuments.net/reader035/viewer/2022062513/554d8a2fb4c9053e0c8b5484/html5/thumbnails/3.jpg)
HICSS 2011 EventGraph
https://casci.umd.edu/HICSS_2011_EventGraph
![Page 4: EventGraphs Talk at HCIL2011](https://reader035.vdocuments.net/reader035/viewer/2022062513/554d8a2fb4c9053e0c8b5484/html5/thumbnails/4.jpg)
EventGraph: n. A specific genre of network graph that illustrates the structure of connections among people discussing an event via social media services like Twitter.1
1Derek Hansen, Marc A. Smith, Ben Shneiderman, "EventGraphs: Charting Collections of Conference Connections," HICSS, pp.1-10, 2011 44th Hawaii International Conference on System Sciences, 2011
![Page 5: EventGraphs Talk at HCIL2011](https://reader035.vdocuments.net/reader035/viewer/2022062513/554d8a2fb4c9053e0c8b5484/html5/thumbnails/5.jpg)
Types of EventGraph Connections
• Conversational Connections: E.g., Mentions, Replies to, Forwards to, Re-Tweets
• Structural Connections: E.g., Follows, is Friends with, is a Fan of
![Page 6: EventGraphs Talk at HCIL2011](https://reader035.vdocuments.net/reader035/viewer/2022062513/554d8a2fb4c9053e0c8b5484/html5/thumbnails/6.jpg)
Taxonomy of EventGraphs
• Duration of event (point events, hours long, days long, weeks long…)
• Frequency of event (one-time, repeated)• Spontaneity of event (planned, unplanned)• Geographic dispersion of event discussants
![Page 7: EventGraphs Talk at HCIL2011](https://reader035.vdocuments.net/reader035/viewer/2022062513/554d8a2fb4c9053e0c8b5484/html5/thumbnails/7.jpg)
Creating EventGraphs in NodeXL
![Page 8: EventGraphs Talk at HCIL2011](https://reader035.vdocuments.net/reader035/viewer/2022062513/554d8a2fb4c9053e0c8b5484/html5/thumbnails/8.jpg)
HICSS
![Page 9: EventGraphs Talk at HCIL2011](https://reader035.vdocuments.net/reader035/viewer/2022062513/554d8a2fb4c9053e0c8b5484/html5/thumbnails/9.jpg)
Analyzing EventGraphs in NodeXL
![Page 10: EventGraphs Talk at HCIL2011](https://reader035.vdocuments.net/reader035/viewer/2022062513/554d8a2fb4c9053e0c8b5484/html5/thumbnails/10.jpg)
What is the Social Structure of an Event Related Discussion?
EventGraph of “oil spill” Twitter data from May 4, 2010 with clusters colored differently and size based on Twitter followers
![Page 11: EventGraphs Talk at HCIL2011](https://reader035.vdocuments.net/reader035/viewer/2022062513/554d8a2fb4c9053e0c8b5484/html5/thumbnails/11.jpg)
Compare DC Week (left) to HICSS (right)
![Page 12: EventGraphs Talk at HCIL2011](https://reader035.vdocuments.net/reader035/viewer/2022062513/554d8a2fb4c9053e0c8b5484/html5/thumbnails/12.jpg)
Who are “Important” Event Discussants?Popular globally
and locally
Popular globally but not locally
Bridge Spanner
Popular locally but not globally
![Page 13: EventGraphs Talk at HCIL2011](https://reader035.vdocuments.net/reader035/viewer/2022062513/554d8a2fb4c9053e0c8b5484/html5/thumbnails/13.jpg)
What is the Nature of the Event Conversation?
![Page 14: EventGraphs Talk at HCIL2011](https://reader035.vdocuments.net/reader035/viewer/2022062513/554d8a2fb4c9053e0c8b5484/html5/thumbnails/14.jpg)
Theorizing The Web 2011 (@ttw2011)(Size = Total Twitter Follower)
https://casci.umd.edu/TTW2011_EventGraph
![Page 15: EventGraphs Talk at HCIL2011](https://reader035.vdocuments.net/reader035/viewer/2022062513/554d8a2fb4c9053e0c8b5484/html5/thumbnails/15.jpg)
Theorizing The Web 2011 (@ttw2011)(Size = Betweenness Centrality)
https://casci.umd.edu/TTW2011_EventGraph
![Page 16: EventGraphs Talk at HCIL2011](https://reader035.vdocuments.net/reader035/viewer/2022062513/554d8a2fb4c9053e0c8b5484/html5/thumbnails/16.jpg)
HCIL Symposium 2011 (#hcil OR hcil)(Size based on Total Twitter Follower)
https://casci.umd.edu/HCIL2011
![Page 17: EventGraphs Talk at HCIL2011](https://reader035.vdocuments.net/reader035/viewer/2022062513/554d8a2fb4c9053e0c8b5484/html5/thumbnails/17.jpg)
HCIL Symposium 2011 (#hcil OR hcil)(Size based on Betweenness Centrality)
https://casci.umd.edu/HCIL2011
![Page 18: EventGraphs Talk at HCIL2011](https://reader035.vdocuments.net/reader035/viewer/2022062513/554d8a2fb4c9053e0c8b5484/html5/thumbnails/18.jpg)
HCIL Symposium 2011 (#hcil OR hcil)(Size based on Betweenness Centrality; Discussion only)
https://casci.umd.edu/HCIL2011
![Page 19: EventGraphs Talk at HCIL2011](https://reader035.vdocuments.net/reader035/viewer/2022062513/554d8a2fb4c9053e0c8b5484/html5/thumbnails/19.jpg)
Caveats
• EventGraphs are only as good as their data– Keywords with low recall (#ashcloud, #ashtag) or precision
(Jaguar)– Not everyone Tweets (HICSS vs. South by Southwest)
• Twitter usage patterns confounded with underlying social network relationships (not a problem for conversational analysis)
• Size limitations for visualizations to be meaningful
![Page 20: EventGraphs Talk at HCIL2011](https://reader035.vdocuments.net/reader035/viewer/2022062513/554d8a2fb4c9053e0c8b5484/html5/thumbnails/20.jpg)
EventGraph Uses
• Conference Attendees– Find people you want to meet (and who can introduce you)– Assess reputation of speakers– Find subgroups you fit in, and those you’re not connected to
• Conference Organizers– Provide an appealing visual representation of conference– Demonstrate role of bridging different communities– Demonstrate value of creating new connections (by
comparing before/after EventGraphs)– Look for subgroups that could form SIGs
![Page 21: EventGraphs Talk at HCIL2011](https://reader035.vdocuments.net/reader035/viewer/2022062513/554d8a2fb4c9053e0c8b5484/html5/thumbnails/21.jpg)
Future Work
• Automated query expansion/refinement (particularly for unplanned events)
• Event detection algorithms and hashtag recommendations
• Overlaying text-based attributes (e.g., sentiment analysis)
• Integrating EventGraphs and events• Developing metrics that identify individuals that
benefit most from events