what's congress doing on twitter?
DESCRIPTION
CSCW 2013 Talk, including supplementary slides As Twitter becomes a more common means for officials to communicate with their constituents, it becomes more important that we understand how officials use these communication tools. Using data from 380 members of Congress’ Twitter activity during the winter of 2012, we find that officials frequently use Twitter to advertise their political positions and to provide information but rarely to request political action from their constituents or to recognize the good work of others. We highlight a number of differences in communication frequency between men and women, Senators and Representatives, Republicans and Democrats. We provide groundwork for future research examining the behavior of public officials online and testing the predictive power of officials’ social media behavior.TRANSCRIPT
WHAT’S CONGRESS DOING ON TWITTER?Libby Hemphill (@libbyh)
Jahna Otterbacher
Matthew A. Shapiro
Illinois Institute of Technology
Congress’s Tweets/Day
0
500
1000
1500
2000
2500
3000
Descriptive Statistics
N Median S.D. Range
Overall 35,361 1,090 2,134 18-8,893
By Females 5,535 760 873 60-3,677
By Males 29,826* 1,155 2,262 18-8,893
By Republicans 21,253* 1,228 2,544 51-8,893
By Democrats 13,648 825 799 18-3,005
By Independents 460 3,372 0 3,372
By Representatives 28,834* 1,055 2,266 18-8,893
By Senators 6,527 1,219 1.396 165-5,927
* Marks groups who were significantly more active than
their counterparts.
Coding• Getting Code Agreement: 6 coders, 791 tweets, excluding
RTs• Training Data: 526 tweets with binary values for each of 5
codes• Coding Process: Mallet’s MaxEnt classifier on 30,373
tweets
Data• 380 members of Congress• 12/20/2011 – 2/29/2012
Tweets as Speech-Acts
• “in saying something, we do something” – Austin, 1962
•Performance•Goal-orientation
Speech-act Frequencies
Directing to Information
Positioning Narrating Thanking Requesting action
0
2000
4000
6000
8000
10000
12000
14000
Directing to Information – 41%
The Bureau of Labor Statistics
reports today that the US economy
added 200,000 jobs in Dec.
Unemployment falls to 8.5%.
http://t.co/WHZO7RaR
(Rep. Andre Carson, D-IN)
Positioning – 22%
President Obama is again bypassing Congress-this time to give amnesty to an untold number of illegal immigrants- http://t.co/KhqoQBCQ
(Rep. Walter Jones, R-NC)
House Republicans refused to let me speak on House floor today. GOP needs to return to work on #payrolltaxcut. Video: http://t.co/YwZFxwWb
(Rep. Jim Moran, D-VA)
Narrating – 7%
I'm talking to CNN's @randikayecnn
at 1:15pm ET and MSNBC's
@mitchellreports at 1:45pm ET
please tune in! #nhprimary #FITN
(Rep. Debbie Wasserman Schultz,
D-FL)
Thanking – 2%
Thank u Matt Strawn for the
successful leadership u gave to
IaGOP Enjoy a rest. Pls continue to
help us in someway to ur liking
(Sen. Chuck Grassley, R-IA)
Requesting Action – 1%
RSVP to my Immigration Forum
with Rep. Luis Gutierrez this
Saturday in Brooklyn
http://t.co/qTcWugs
(Rep. Yvette Clark, D-NY)
BETWEEN GROUP COMPARISONS
Directing to Information – By Party
Directing to Information – By Sex
Directing to Information – By Chamber
Positioning – By Party
Positioning – By Sex
Positioning – By Chamber
Requesting Action – By Party
Requesting Action – By Sex
Requesting Action – By Chamber
Thanking – By Party
Thanking – By Sex
Thanking – By Chamber
SPEECH-ACTS, AUDIENCE, AND VOTING
Moderated effects – Twitter-action and sub-group – upon following
Speech-Act Narrating Positioning Providing info
Requesting action
Thanking
Male GOP - - -Female GOP
- - -Male Dem - -Female Dem - -F-stat 18.47*** 17.72*** 18.10*** 17.88*** 18.52***
R2 0.02 0.02 0.02 0.02 0.02
Action tweets’ effects on audience size
Mal
e co
nser
vativ
es
Femal
e co
nser
vativ
es
Mal
e lib
eral
s
Femal
e lib
eral
s-100%
-80%
-60%
-40%
-20%
0%
20%
40%
60%
80%
thanksrequest actionproviding infopositioningnarrative
Predicting Voting Behavior using Frequency of PositioningDependent variable DW-NOMINATE
Speech-act Positioning (raw)
Male GOP (baseline)
0.001*
Female GOP -0.101
Male Dem -0.206***
Female Dem -0.160***
F-stat 27.47
R2 0.27
Takeaways
•Men, Republicans, Representatives
more active
•Broadcast mechanism
• Implicitly campaigning all the time
•Effects on audience not uniform
•More positioning, more polarized
WHERE DO WE GO FROM HERE?
Ongoing Work
• Is Congress polarized like the public?• Does Twitter provide an alternate path to influence?
• How do politicians interact with their constituents?
• How do constituents interact with their politicians?
• What’s happening in the EU? South Korea?
Contact us
• Libby Hemphill ([email protected]; @libbyh)
• Jahna Otterbacher ([email protected])
• Matt Shapiro ([email protected])
Illinois Institute of Technology
@casmlab
http://www.casmlab.org/projects/publicofficials/
https://twitter.com/CaSMLab/lists
SUPPLEMENTARY SLIDES
Why study Congress?• > 90% adoption rate• ~650 tweets per day• Reaching > 35K followers
• Plenty of hype• No traditional media corporation mediating conversation
between officials and constituents
Coding
Golbeck, Grimes, and Rogers
• Getting Code Agreement: 3 coders, 200 tweets
• Coding Process: 3 coders each coded 2/3; 4,626 tweets
• Agreement: Included only tweets with identical codes from two coders
• Codes: Tree scheme, some branches mutually exclusive
Our Study
• Getting Code Agreement: 6 coders, 791 tweets, excluding RTs
• Training Data: 526 tweets with binary values for each of 5 codes
• Coding Process: Mallet’s MaxEnt classifier on 35,361 tweets
Code DefinitionCohen’s kappa N (%)
Narrating Telling a story about their day, describing activities
0.83 2,069
(7%)
Positioning Situating one's self in relation to another politician or political issue, may be implied rather than explicit
0.87 6,728
(22%)
Directing to information
Pointing to a resource URL, telling you where you can get more info
0.70 12,468
(41%)
Requesting action Explicitly telling followers to go do something online or in person (not just visiting a link but asking them to do something like sign a petition, apply, vote) - look for action verbs
0.70 299
(1%)
Thanking Says nice things about or thanks someone else, e.g. congratulations, compliments
0.90 667
(2%)
Comparing automated classifiersClassifier Narr Posit Info ReqAc ThankBayes 0.78 0.74 0.86 0.84 0.90 -0.02 -0.08 -0.06 -0.04 -0.03No stop words 0.74 0.72 0.81 0.73 0.82 -0.05 -0.05 -0.04 -0.09 -0.05DecisionTree 0.80 0.60 0.91 0.91 0.96 -0.05 -0.07 -0.04 -0.04 -0.01No stop words 0.79 0.61 0.90 0.91 0.93 -0.06 -0.05 -0.05 -0.06 -0.04MaxEnt 0.83 0.71 0.91 0.91 0.95 -0.05 -0.06 -0.03 -0.03 -0.03No stop words 0.80 0.71 0.91 0.91 0.93 -0.07 -0.07 -0.04 -0.03 -0.04
Comparing tweet frequency
Model 1 Model 2 Model 3 Model 4
Male 943.309 597.863 593.203 585.361
Republican 1110.179 1105.994 1201.930
Senate -113.932 -134.147
Days in Office 0.077
Constant 1080.438 704.562 732.038 427.333
r2 0.026 0.087 0.088 0.101
All coefficients significant; p < 0.001
Information SourcesDomain Tweets
YouTube.com 2348
Facebook.com 1495
yfrog.com 667
speaker.gov 480
TheHill.com 391
TwitPic.com 321
politico.com 301
online.wsj.com 298
washingtonpost.com 295
Flickr.com 284
Moderated effects – Twitter-action and sub-group – upon following: U-S
Dependent variable in logs
(1)# Followers
(2)# Followers
(3)# Followers
(4)# Followers
(5)# Followers
Speech-Act Narrating Positioning Providing info
Requesting action
Thanking
Male conservatives (baseline)
0.07(0.08)
-0.05(0.04)
-0.01(0.04)
-0.29(0.16)
0.23(0.11)
Female conservatives
-0.01(0.21)
0.09(0.11)
-0.04(0.11)
-0.42(0.45)
0.26(0.36)
Male liberals
-0.22(0.13)
0.12(0.07)
0.09(0.07)
0.27(0.27)
-0.52(0.19)
Female liberals
0.34(0.18)
-0.09(0.11)
0.23(0.10)
0.35(0.48)
-0.45(0.30)
F-stat 18.47*** 17.72*** 18.10*** 17.88*** 18.52***
R2 0.02 0.02 0.02 0.02 0.02
Predicting Voting Behavior using Relative Frequency of PositioningDependent variable DW-Nom.
Speech-act Positioning
Male GOP (baseline)
0.073
Female GOP -0.109*
Male Dem -0.211***
Female Dem -0.156***
F-stat 28.9
R2 0.29
Positioning tweets’ effects on DW-NOMINATE – by subgroup
Male
con
serv
ative
s
Female
con
serv
ative
s
Male
liber
als
Female
liber
als-0.04
-0.02
0
0.02
0.04
0.06
0.08
0.1
Future Work
•Government Responsiveness• Constituent lobbying efforts• @ replies from MoCs
•Civic Engagement• Voting records• Non-voting political activities