Transcript EventGraphs: mapping the social structure of events with NodeXL

EventGraphs: mapping the social
structure of events with NodeXL
Mass Conversations of Events
Research Goal: Augment people’s ability to make sense of
mass conversations of events
HICSS 2011 EventGraph
https://casci.umd.edu/HICSS_2011_EventGraph
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
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
Creating EventGraphs in NodeXL
HICSS
Analyzing EventGraphs in NodeXL
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
Compare DC Week (left) to HICSS (right)
Who are “Important” Event Discussants?
Popular globally
and locally
Bridge Spanner
Popular locally
but not globally
Popular globally
but not locally
What is the Nature of the Event
Conversation?
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
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
http://nodexl.codeplex.com
Theorizing The Web 2011 (@ttw2011)
Theorizing The Web 2011 (@ttw2011)
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
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