Visualizing Communication on Social Media: Making Big Data Accessible Karissa McKelvey, Alex Rudnick Michael Conover and Filippo Menczer Center for Complex Networks and Systems Research School of Informatics and Computing Indiana University, Bloomington truthy.indiana.edu 1
Visualizing Communication on Social Media: Making Big Data Acessible
Jan 27, 2015
Presented at CSCW 2012 Workshop on Community Discourse and Action
Welcome message from author
This document is posted to help you gain knowledge. Please leave a comment to let me know what you think about it! Share it to your friends and learn new things together.
Transcript
Visualizing Communication on Social Media:
Making Big Data AccessibleKarissa McKelvey, Alex Rudnick
Michael Conover and Filippo Menczer
Center for Complex Networks and Systems ResearchSchool of Informatics and Computing
Indiana University, Bloomington
truthy.indiana.edu 2
truthy.indiana.edu 3
truthy.indiana.edu 4
truthy.indiana.edu 5
truthy.indiana.edu 6
truthy.indiana.edu 7
8
truthy.indiana.edu 9
truthy.indiana.edu 10
truthy.indiana.edu 11
Can we use social media as laboratories for social
science?
truthy.indiana.edu 12
Social Scientists
Computer Scientists
?
13
truthy.indiana.edu
Enables the study of discourse in large-scale social media by collecting, analyzing, classifying, visualizing, and modeling massive streams of public micro-blogging data
truthy.indiana.edu 14
#tcot
truthy.indiana.edu 15
Meme
Hashtag
truthy.indiana.edu 16
Meme
Hashtag
User
truthy.indiana.edu 17
Meme
Hashtag
User
URL
truthy.indiana.edu 18
Meme
Hashtag
User
URL
Phrase
celebrities
spam
astroturf
politics
19
truthy.indiana.edu 20
politics
truthy.indiana.edu 21
#tcot
truthy.indiana.edu 22
celebrities
politics
truthy.indiana.edu 23
@barackobama
celebrities
spam
astroturf
politics
24
truthy.indiana.edu 25
@bek_rt
truthy.indiana.edu 26
truthy.indiana.edu 27
network structure
truthy.indiana.edu 28
political affiliation
network structure
truthy.indiana.edu 29
political affiliation
language detection
network structure
truthy.indiana.edu 30
sentiment
political affiliation
language detection
network structure
truthy.indiana.edu 31
Existing visualizations
32
33
34
35
truthy.indiana.edu 36
New Visualizations
truthy.indiana.edu 37
New Visualizations
Interactive Meme Diffusion Network
truthy.indiana.edu 38
#tcot
truthy.indiana.edu 39
#tcot#tcot
40
#tcot#tcot
41
#tcot#tcot
42
#tcot#tcot
43
#tcot#tcot
44
#tcot#tcot
45
#tcot#tcot
truthy.indiana.edu 46
#usa
truthy.indiana.edu 47
truthy.indiana.edu 48
truthy.indiana.edu 49
New Visualizations
User Data Exploration Interface
truthy.indiana.edu 50
51
52
53
truthy.indiana.edu 54
Future Work
Time
truthy.indiana.edu 55
Future Work
Space
truthy.indiana.edu 56
Future Work
Feedback
truthy.indiana.edu 57
truthy.indiana.edu 58
ThanksPapers at cnets.indiana.edu/groups/nan/truthy
Sandro Flammini
Bruno Conçalves
Jacob Ratkiewicz
Lilian Weng
Mike Conover
Johan Bollen
Przemek Grabowicz
Mark Meiss
Alex Vespignani
Alex Rudnick
Luca Aiello
Filippo Menczer
truthy.indiana.edu 60
Content injection• Please follow @username for an outstanding progressive voice!
#p2 #dems #prog #democrats #tcot
• Couple Aborts Twin Boys For Being Wrong Gender .. http://bit.ly/xyz #tcot #hhrs #christian #tlot #teaparty #sgp #p2 #prolife
Importance of content stream (hashtagtag) t in group A
truthy.indiana.edu 61
Predicting Political Alignment
1000 manually labeled users
Features AccuracyText (TF-IDF) 79%
Hashtags 91%
Retweet network 95%
Tags + Network 95%
LSA (users-tags)
truthy.indiana.edu 62
Cross-ideological interactions
Valence of a hashtag
#dems#p2#healthcare#dreamact
#sgp#twisters#foxnews#abortion
truthy.indiana.edu 63
Competition for attention
• Some memes go viral, most do not• Is this due to intrinsic value of memes?
User activity, popularity, influence? Topic persistence? Homophily? External media?...
#jan25
Related Documents
