This is a presentation given at the ICWSM 2010 in Washington, DC (www.icwsm.org). You can watch a video of the presentation on videolectures.net
Twitter is a microblogging website where users read and write millions of short messages on a variety of topics every day. This study uses the context of the German federal election to investigate whether Twitter is used as a forum for political deliberation and whether online messages on Twitter validly mirror offline political sentiment. Using LIWC text analysis software, we conducted a content-analysis of over 100,000 messages containing a reference to either a political party or a politician. Our results show that Twitter is indeed used extensively for political deliberation. We find that the mere number of messages mentioning a party reflects the election result. Moreover, joint mentions of two parties are in line with real world political ties and coalitions. An analysis of the tweets’ political sentiment demonstrates close correspondence to the parties' and politicians’ political positions indicating that the content of Twitter messages plausibly reflects the offline political landscape. We discuss the use of microblogging message content as a valid indicator of political sentiment and derive suggestions for further research.
2. Agenda
Introduction and related research
Data set and methodology
Results and implications
1
3. The successful use of social media in the last presidential campaign has
established Twitter as an integral part of the political campaign toolbox
The increasing use of Twitter as mean of …has triggered attempts to better understand
political communication… and aggregate this information
The Library of Congress recently
acquired the entire Twitter archive
2
4. The goal of our study was to explore 3 research questions
Research questions
1 Deliberation
Does Twitter provide a platform for
political deliberation online?
2 Sentiment
How accurately can Twitter inform
us about the electorate's political
sentiment?
3 Prediction
Can Twitter serve as a predictor of
the election result?
3
5. Existing research related to our research questions and SELECTED EXAMPLES
resulting research gaps we try to address
Research questions Related research Research gap
1 Deliberation Twitter is not only used for one-way Many contexts largely
communication, but 31% of all tweets direct a unexplored, e.g. the
Does Twitter provide specific addressee (Honeycut&Herring, 2009) political debate online
a platform for Political internet discussion boards found to Unclear whether
political deliberation be dominated by a small number of heavy findings apply to
online? users (Koop&Jansen, 2009) microblogging forums
2 Sentiment 19% of all tweets contain mentions of a brand Limited application to
or product and statistically significant political sentiment
How accurately can differences of customer sentiment can be
Twitter inform us extracted (Jansen et al., 2009)
about the Pessimism towards the ability of blogs to Few empirical studies
electorate's political aggregate dispersed bits of information to explore information
sentiment? (Sunstein, 2008) aggregation in social
media
3 Prediction Some studies explore the reflection of the Unclear whether
political landscape in "traditional" weblogs findings apply to
and social media (e.g., number of Facebook microblogging forums
Can Twitter serve as users a valid indicator of electoral success,
a predictor of the Williams&Gulati, 2008)
election result? Count of candidate mentions in the press can
be a better predictor of election results than
official election polls (Véronis, 2007)
Previous studies have shown that social media
can reflect the political landscape offline, but
focused on "traditional" weblogs/message boards
4
6. Agenda
Introduction and related research
Data set and methodology
Results and implications
5
7. We examined more than 100,000 tweets and extracted their sentiment
using LIWC
Data set Methodology
104,003 political tweets Linguistic Inquiry and Word Count (by James
Published between August 13th and September Pennebaker et al.)
19th, 2009 (one week prior to the election) Text analysis software developed to assess
Collected all tweets containing the name of emotional, cognitive, and structural
either components of text samples using a
At least one of the 6 major parties psychometrically validated dictionary
Selected prominent politicians Calculates the share of words in a text
belonging to empirically defined psychological
and structural dimensions
LIWC has been used widely in psychology and
linguistics including to
Measure the sentiment levels in US Senatorial
(Yu et al., 2008)
Profile politicians Twitter messages
6
8. Background on the situation prior to the German federal PRE-ELECTION
election 2009 Governing grand coalition
Parties in the German Bundestag 2005-09
Socialists Social Democrats Green Party Liberals Christian Democrats
Grouping of former SPD candidate for Historical coalition Publicly committed Union*-Chancellor
East German state Chancellor partner of SPD, to coalition with Merkel running for
party and leftist Steinmeier but with limited CDU reelection
SPD-defectors rejected Die Linke chances for Spent 8 years in Favoring a
Recent rise frag- as possible government the opposition coalition with the
mented political coalition partner participation FDP
spectrum
Potential coalition of CDU and
FDP was leading by a slight
majority in most polls
* CDU and CSU, often referred to as the "Union", are sister parties which form one faction in the German parliament
7
9. Agenda
Introduction and related research
Data set and methodology
Results and implications
8
10. While Twitter is used as a forum for political deliberation on
1 substantive issues, this forum is dominated by heavy users
Two widely accepted indicators of blog-based deliberation…
The exchange of substantive issues Equality of participation
Party Sample tweet* Users Messages
CDU CDU wants strict rules for internet User group Total Share Total Share
CSU CSU continues attacks on partner of choice One-time users 7,064 50.3% 7,064 10.2%
FDP
Light (2-5) 4,625 32.9% 13,353 19.3%
FDP Whoever wants civil rights must choose Medium (6-20) 1,820 12.9% 18,191 26.2%
FDP!
Heavy (21-79) 463 3.3% 15,990 23.1%
Grüne After the crisis only Green can help
GREEN+ Very heavy (80+) 84 0.6% 14,470 21.2%
Total 14,056 100% 69,318 100%
SPD Only a matter of time until the SPD
dissolves
While the distribution of users across user
Die Linke Society for Human Rights recommends: No groups is almost identical with the one found on
government partication for LINKE internet message boards, we find even less
equality of participation for the political debate on
31% of all messages contain "@"-sign Twitter
19% of all messages are retweets Additional analyses have shown users to exhibit
a party-bias in the volume and sentiment of their
* Examples shortened for citation (e.g. omission of hyperlinks)
Source: Jansen&Koop (2009)
messages
9
11. The online sentiment in tweets reflects nuanced offline
2 differences between the politicians in our sample
LIWC profiles*
Leading candidates Other politicians
Very similar profile for all leading candidates Positive outweigh negative emotions, except in the
Only polarizing political characters, such as liberal case of CSU leader Seehofer who in addition is
leader Westerwelle and socialist Lafontaine, associated the most with anger (he irritated many
deviate in line with their roles as opposition voters with his attacks on desired coalition partner
leaders FDP)
Messages mentioning Steinmeier, who was For Steinbrück and zu Guttenberg, the issues
sending mixed signals regarding potential coalition money and work, reflect their roles as finance and
partners, are the most tentative economics minister
* We focused on the 12 dimensions which a priori seemed best suited to profile sentiment and political issues
Source: Jansen&Koop (2009)
10
12. The similarity of profiles is a plausible reflection of the political
2 proximity between the parties
Similarity of LIWC profiles
Group Distance* Key findings
Politicians
All politicians 0.21 High convergence of the leading
candidates
Governing coalition 0.23 More divergence among
Right coalition 0.16 politicians of the governing grand
Distance measure to quantify coalition than among those of a
the similarity of sentiment Left coalition 0.10 potential right wing coalition
profiles The similar profiles of Merkel and
Candidates for chancellor 0.02 Steinmeier mirror the consensus-
driven style of their grand coalition
Leading candidates 0.10
Other candidates 0.24
Parties
All parties 0.09 The fit of a potential right-wing
coalition is almost as good as the
Governing coalition 0.07 fit in the governing coalition
Right coalition 0.08 Greatest divergence among
parties on the left
Left coalition 0.10 Tight fit between sister parties
CDU and CSU
Union 0.01
* Average distance from the mean profile per category across all 12 dimensions in percentage points
11
13. The activity on Twitter prior to the election seems to validly
3 reflect the election outcome
The share of tweets can be considered a plausible …and joint party mentions accurately reflect the political
reflection of the election results… ties between parties
All mentions Election results Relative frequency of joint mentions**
Vote CDU CSU SPD FDP Linke
Party Total Share share Error
CDU 30,886 30.1% 29.0% 1.0% CSU 1.25*
CSU 5,748 5.6% 6.9% 1.3% SPD 1.23* 0.71*
SPD 27,356 26.6% 24.5% 2.2% FDP 1.04* 1.01 0.90*
FDP 17,737 17.3% 15.5% 1.7% Die Linke 0.81* 0.79* 1.04* 0.97
Die Linke 12,689 12.4% 12.7% 0.3% Grüne 0.84* 0.79* 0.98 1.06* 1.18*
Grüne 8,250 8.0% 11.4% 3.3%
MAE = 1.65%
Research institute MAE (last poll)
Forsa 0.84% An analysis of messages surrounding the TV
Forschungsgruppe Wahlen 1.04% debate between the main candidates has
shown that tweets can also reflect the
GMS 1.48% sentiment over time
Infratest/dimap 1.40%
* Significant at the .05-level
** Measures how often two parties are mentioned together relative to the random probability
12
14. Our findings suggest the use of social media information content to
complement insights regarding the public's political sentiment
Research questions Conclusions
1 Deliberation While we find evidence of a lively political debate on Twitter,
Does Twitter this discussion is dominated by a small number of users:
provide a only 4% of all user account for more than 40% of the
platform for messages
political
deliberation
online?
2 Sentiment Sentiment profiles plausibly reflect many nuances of the
How accurately election campaign
can Twitter Politicians evoke a more diverse set of profiles than parties
inform us about Similarity of profiles is indicative of the parties' proximity with
the electorate's respect to political issues
political
sentiment?
3 Prediction In contrast with previous studies of political message
boardes, we find that the mere number of messages reflects
Can Twitter serve
the election results and even comes close to traditional
as a predictor of
election polls
the election
Joint party mentions mirror closeness on political issues and
result?
likely coalitions
13
16. hank you for your attention!
Stay tuned @TUitter_2010
15
17. References (1/2)
• Adamic, L. A., and Glance, N. 2005. The political blogosphere and the 2004 US election: Divided they blog. In
Proceedings of the 3rd International Workshop on Link Discovery, 36-43. Chicago, IL.
• Albrecht, S.; Lübcke, M.; and Hartig-Perschke, R. 2007. Weblog Campaigning in the German Bundestag Election 2005.
Social Science Computer Review, 25(4): 504-520.
• Böhringer, M., and Richter, A. 2009. Adopting Social Software to the Intranet: A Case Study on Enterprise Microblogging.
In Proceedings of the 9th Mensch & Computer Conference, 293-302. Berlin.
• Drezner, D.W., and Henry F. 2007. Introduction: Blogs, politics and power: a special issue of Public Choice. Public
Choice, 134(1-2): 1-13.
• Farrell, H., and Drezner D.W. 2008. The power and politics of blogs. Public Choice. 134(1-2): 15-30.
• Gueorguieva, V. 2007. Voters, MySpace, and YouTube: The Impact of Alternative Communication Channels on the 2006
Election Cycle and Beyond. Social Science Computer Review, 26(3): 288-300.
• Honeycutt, C., and Herring, S. C. 2009. Beyond microblogging: Conversation and collaboration via Twitter. In 42nd
Hawaii International Conference on System Sciences, 1-10, Hawaii.
• Huber, J., and Hauser, F. 2005. Systematic mispricing in experimental markets–evidence from political stock markets. In
10th Annual Workshop on Economic Heterogeneous Interacting Agents. Essex, UK.
• Huberman, B. A.; Romero, D. M.; and Wu, F. 2008. Social Networks that Matter: Twitter Under the Microscope. Retrieved
on December 15, 2009 from http://ssrn.com/abstract=1313405
• Jansen, B. J.; Zhang, M.; Sobel, K.; and Chowdury, A. 2009. Twitter power: Tweets as electronic word of mouth. Journal
of the American Society for Information Science and Technology, 60: 1–20.
• Jansen, HJ, and Koop. R. 2005. Pundits, Ideologues, and Ranters: The British Columbia Election Online. Canadian
Journal of Communication, 30(4): 613-632.
• Java, A.; Song, X.; Finin, T.; and Tseng, B. 2007. Why we twitter: understanding microblogging usage and communities.
In Proceedings of the 9th WebKDD and 1st SNA-KDD 2007 workshop on Web mining and social network analysis, 56–
65. San Jose, CA: ACM.
• Koop, R., and Jansen, H. J. 2009. Political Blogs and Blogrolls in Canada: Forums for Democratic Deliberation? Social
Science Computer Review, 27(2): 155-173.
• McKenna, L., and Pole A. 2007. What do bloggers do: an average day on an average political blog. Public Choice, 134(1-
2): 97-108.
• Meckel, M., and Stanoevska-Slabeva K. 2009. Auch Zwitschern muss man üben - Wie Politiker im deutschen
Bundestagswahlkampf twitterten. Retrieved December 15 from: http://www.nzz.ch/nachrichten/kultur/medien/
auch_zwitschern_muss_man_ueben_1.3994226.html
16
18. References (2/2)
• Nielsen Media Research. 2009. Das Phänomen Twitter in Deutschland. Retrieved December 15, 2009 from
http://de.nielsen.com/news/ NielsenPressemeldung04.08.2009-Twitter.shtml
• Perlmutter, D. D. 2008. Political Blogging and Campaign 2008: A Roundtable. The International Journal of Press/Politics,
13(2): 160-170.
• Pennebaker, J.; Chung, C.; and Ireland, M. 2007. The development and psychometric properties of LIWC2007. Austin,
TX.
• Schneider, S. M. 1996. Creating a Democratic Public Sphere Through Political Discussion. Social Science Computer
Review, 14(3): 373-392.
• Skemp, K. 2009. All A-Twitter about the Massachusetts Senate Primary. Retrieved December 15, 2009 from
http://bostonist.com/2009/12/01/ massachusetts_senate_primary_debate_twitter.php
• Sunstein, Cass. 2007. Neither Hayek nor Habermas. Public Choice, 134(1-2): 87-95.
• Tausczik, Y. R., and Pennebaker, J. W. 2009. The Psychological Meaning of Words: LIWC and Computerized Text
Analysis Methods. Journal of Language and Social Psychology.
• Véronis, J. 2007. Citations dans la presse et résultats du premier tour de la présidentielle 2007. Retrieved December 15,
2009 from http://aixtal.blogspot.com/ 2007/04/2007-la-presse-fait-mieux-que-les.html
• Williams, C., and Gulati, G. 2008. What is a Social Network Worth? Facebook and Vote Share in the 2008 Presidential
Primaries. In Annual Meeting of the American Political Science Association, 1-17. Boston, MA.
• Woodly, D. 2007. New competencies in democratic communication? Blogs, agenda setting and political participation.
Public Choice, 134(1-2): 109-123.
• Yu, B.; Kaufmann, S.; and Diermeier, D. 2008. Exploring the characteristics of opinion expressions for political opinion
classification. In Proceedings of the 2008 international conference on Digital government research, 82-91. Montreal.
• Zarrella, D. 2009a. State of the Twittersphere. Retrieved December 15, 2009 from:
http://blog.hubspot.com/Portals/249/sotwitter09.pdf
• Zarrella, D. 2009b. The Science of Retweets. Retrieved December 15, 2009 from: http://danzarrella.com/the-science-of-
retweets-report.html
• pearanalytics 2009. Twitter Study. Retrieved December 15, 2009 from http://www.pearanalytics.com/ wp-
content/uploads/2009/08/Twitter-Study-August-2009.pdf
17
19. EXAMPLES
Limitations of our research
Limitation Description Mitigating arguments/research gaps
Research on political bloggers (McKenna and The fact that these well-educated users
Pole 2008) and similar demographics of "influence important actors within
Twitter users (pearanalytics 2009) suggest mainstream media who in turn frame issues
Sample selection that our sample may not have been for a wider public" (Farrel and Drezner
representative of the German electorate 2008, p. 29) warrants special attention to
Twitter as a source of opinion leadership.
Data were limited to the tweets containing the Twitter users include hashtags, in many
names of parties and politicians that we messages (e.g., "#CDU"), so we believe the
defined as search terms share of relevant replies to be small
Search algorithm We may have missed some replies belonging Future research should try to capture the
to a discussion thread because respondents context by following embedded links or by
do not necessarily repeat these names searching for replies to an author.
Our investigation was based on one particular We believe this effect to be negligible since
text analysis software and used an existing LIWC is based on word count only and
dictionary not specifically tailored to classify therefore should not be affected by
Text analysis such short messages as tweets grammatical errors
We treated all messages published in a given Further research should investigate
time frame as one document sentiment one tweet at a time
We have examined overall political sentiment, Future sentiment analysis could address
voters' attitudes and opinions may vary this issue by conducting a more detailed
Definition of depending on specific political issues classification of content.
sentiment
18
20. Users exhibit a party-bias in the volume and sentiment of BACKUP
their messages
Distribution
of attention
by user
group
Share of
tweets and
sentiment
of party-
affiliated
accounts
19