SlideShare a Scribd company logo
1 of 30
Download to read offline
Twitter-based election
prediction in the
developing world
Nugroho Dwi Prasetyo & Claudia Hauff
Twitter-based election polling is a cheap alternative to
traditional “offline” polls.
Twitter-based election polling should achieve
a prediction accuracy similar to traditional polls.
millions of potential voters inferred votes biases
The what & why
@flickr:misteraitch
“No, you cannot predict elections with Twitter.”
D. Gayo-Avello. Internet Computing, IEEE 16.6 (2012): 91-94.
@flickr:misteraitch
“No, you cannot predict elections with Twitter.”
D. Gayo-Avello. Internet Computing, IEEE 16.6 (2012): 91-94.
That hasn’t stopped people from
trying!
@flickr:practicalowl
Germany Federal
Count tweets &
hashtags
5 weeks6 party names 1.7%
Singapore Presidential
Count tweets +
sentiment
1 week4 candidate names 6.1%
USA Presidential
Count tweets +
sentiment
6 months2 candidate names 11.6%
Ireland General
Count tweets +
sentiment
3 weeks5
party names +
election hashtag
3-6%
Netherlands Senate Count tweets 1 month12 Dutch words 1.3%
USA Presidential Count tweets 6 weeks2 N/A 1.7%
Germany Federal
Count hashtags
+ sentiment
4 months6
party names +
election hashtags
N/A
USA, France Presidential sentiment 2 months2
candidate names +
election hashtag
N/A
USA
Republican
nomination
Count tweets +
sentiment
1 year7 candidate names N/A
Venezuela,
Paraguay,
Ecuador
Presidential
Count tweets +
users
7 months
2
3
2
candidate names
and aliases
0.1%-
19%
So far …
Twitter-based predictions lack behind traditional polls.
Most works focus on elections in the developed world.
Traditional polls are accurate.
Traditional polls are conducted often.
So far …
Twitter-based predictions lack behind traditional polls.
Most works focus on elections in the developed world.
What do Twitter-based methods add?
In the developing world
… traditional polls are less likely to be reliable.
… the demographic bias of Twitter users is high.
4.08%
3.45%11.75%
4.21%
12.24%
5.64%
6.25%
1.36%
2.69%
1.19%
7.02%
4.20%
8.84%
0.98%
3.96%
3.13%
4.24%1.15%
0.87%
11.49%
Mean Absolute Error of 20 traditional polls conducted
in the run-up to the 2014 Indonesian presidential election
A detailed analysis of all major factors of Twitter-based
election forecasting with a special emphasis on de-
biasing through “offline” data.
An in-depth comparison of 20 traditional polls and
Twitter-based forecasts for the 2014 Indonesian
presidential election.
Our contributions
@flickr:carbonnyc
Approach
Processing pipeline
(1) Data collection
election type data access duration keywords
(3) Data de-biasing
age gender location
(2) Data filtering
spam organisations geo-location
(4) Election prediction
candidate mentions one vote per user tweet sentiment
The ground truth
election outcome
&
traditional polls
predicted vote %
election vote %#candidates
Use case
&
data
@flickr:rh2ox
2014 Indonesian 

presidential election
Joko Widodo vs. Prabowo Subianto
Widodo won 53.15% of the votes.
Widodo won in 23 of the 33 provinces.
Widodo was supported by the opposition.
July 9, 2014
Gathered tweets
Crawling period
#Electoral tweets
Max. tweets / day
#Users
Max. active users / day
April 15 - July 8, 2014
7,020,228
375,064
490,270
148,135
Manually curated keyword list (updated daily); only tweets
geo-located in Indonesia are included.
POLLDATA
Gathered tweets II
#Users
Most recent 100 tweets per user. Not used for prediction purposes.
USERDATA
Crawling period July 25 - 30, 2014
#Tweets ~42,000,000
490,270
Insights into data
@flickr:edith_soto
Is spam a problem?
7.4% are spam users
2.1% are “slacktivists”
3.8% are non-personal users
Based on a manual classification of 600 randomly selected users in USERDATA
How large is the bias?
Based on a manual classification of 600 randomly selected users in USERDATA
0%
20%
40%
60%
80%
Female Male
Twitter Population
gender
0%
20%
40%
60%
80%
0-19 20-49 50+
Twitter Population
age
How large is the bias?
0%
20%
40%
60%
80%
Female Male
Twitter Population
gender
0%
20%
40%
60%
80%
0-19 20-49 50+
Twitter Population
age
Automatic classification of POLLDATA.
age gender
How large is the bias?
Based on reserve geo-coding & population data for Indonesia.
location
Jakarta
Internet penetration rate: 17%
location
Results
@flickr:nathanmac87
From tweets to users
tweet count 56.45% 3.3% +7 23/3343.55% -13 0.27
W
idodo
Subianto
MAE
traditional
polls
province level
correct min. MAE
26.09
max. MAE
user count 54.45% 1.3% +4 24/3345.55% -16 0.05 25.01
On the national level, “one user one vote” outperforms
tweet-based predictions (confirming prior works).
On the province level the changes are miniscule.
our baselines
Keyword selection
all keywords
candidate name
5 keywords
Simply using more keywords does not always lead
to better results.
Location de-biasing
tweet count 55.14% 2.0% +544.86% -15
W
idodo
Subianto
MAE
traditional
polls
user count 54.26% 1.1% +245.74% -18
Decreasing the influence of tweets from overrepresented
locations in the dataset improves the prediction.
Gender de-biasing
tweet count 56.36% 3.2% +7 21/3343.64% -13 0.33
W
idodo
Subianto
MAE
traditional
polls
province level
correct min. MAE
28.05
max. MAE
user count 54.89% 1.7% +5 23/3345.11% -15 0.10 26.72
Correcting for gender biases degrades the prediction
accuracy on the national & province level.
Impact of sentiment
tweet count 53.98% 0.8% +046.02% -20
W
idodo
Subianto
MAE
traditional
polls
province level
correct min. MAE max. MAE
user count 54.02% 0.9% +045.98% -20
On the national level, sentiment yields the best forecast.
tweet count 50.67% 2.5% +549.33% -15
user count 53.77% 0.6% +046.23% -20
14/33 0.01 54.90
19/33 0.26 26.51
14/33 0.01 49.79
19/33 0.01 26.40
POSPOS+NEG
The impact on the province level prediction is negative.
Impact of sentiment
tweet count 53.98% 0.8% +046.02% -20
W
idodo
Subianto
MAE
traditional
polls
province level
correct min. MAE max. MAE
user count 54.02% 0.9% +045.98% -20
On the national level, sentiment yields the best forecast.
tweet count 50.67% 2.5% +549.33% -15
user count 53.77% 0.6% +046.23% -20
14/33 0.01 54.90
19/33 0.26 26.51
14/33 0.01 49.79
19/33 0.01 26.40
POSPOS+NEG
The impact on the province level prediction is negative.
More than 700 languages
are spoken in Indonesia
Conclusions
Simple Twitter-based predictors outperform (almost) all
traditional polls in Indonesia.
Accurate predictions on province level are challenging,
due to data sparsity & data diversity.
Currently: designing a Web application prototype to
automatically observe ongoing elections.
Thank you.
c.hauff@tudelft.nl

More Related Content

Viewers also liked

Learning by example: training users through high-quality query suggestions
Learning by example: training users through high-quality query suggestionsLearning by example: training users through high-quality query suggestions
Learning by example: training users through high-quality query suggestionsClaudia Hauff
 
Large-scale Learning Analytics at TU Delft
Large-scale Learning Analytics at TU DelftLarge-scale Learning Analytics at TU Delft
Large-scale Learning Analytics at TU DelftClaudia Hauff
 
janice mister cv_03.17
janice mister cv_03.17janice mister cv_03.17
janice mister cv_03.17Janice Mister
 
Learner profiling beyond the MOOC platform
Learner profiling beyond the MOOC platformLearner profiling beyond the MOOC platform
Learner profiling beyond the MOOC platformClaudia Hauff
 
Dagstuhl Search as Learning: seminar introduction
Dagstuhl Search as Learning: seminar introductionDagstuhl Search as Learning: seminar introduction
Dagstuhl Search as Learning: seminar introductionClaudia Hauff
 
Dagstuhl Search as Learning: summary breakout 1
Dagstuhl Search as Learning: summary breakout 1Dagstuhl Search as Learning: summary breakout 1
Dagstuhl Search as Learning: summary breakout 1Claudia Hauff
 
Big Data in Learning Analytics - Analytics for Everyday Learning
Big Data in Learning Analytics - Analytics for Everyday LearningBig Data in Learning Analytics - Analytics for Everyday Learning
Big Data in Learning Analytics - Analytics for Everyday LearningStefan Dietze
 
How to give a good 10min presentation
How to give a good 10min presentation How to give a good 10min presentation
How to give a good 10min presentation Jodie Martin
 

Viewers also liked (8)

Learning by example: training users through high-quality query suggestions
Learning by example: training users through high-quality query suggestionsLearning by example: training users through high-quality query suggestions
Learning by example: training users through high-quality query suggestions
 
Large-scale Learning Analytics at TU Delft
Large-scale Learning Analytics at TU DelftLarge-scale Learning Analytics at TU Delft
Large-scale Learning Analytics at TU Delft
 
janice mister cv_03.17
janice mister cv_03.17janice mister cv_03.17
janice mister cv_03.17
 
Learner profiling beyond the MOOC platform
Learner profiling beyond the MOOC platformLearner profiling beyond the MOOC platform
Learner profiling beyond the MOOC platform
 
Dagstuhl Search as Learning: seminar introduction
Dagstuhl Search as Learning: seminar introductionDagstuhl Search as Learning: seminar introduction
Dagstuhl Search as Learning: seminar introduction
 
Dagstuhl Search as Learning: summary breakout 1
Dagstuhl Search as Learning: summary breakout 1Dagstuhl Search as Learning: summary breakout 1
Dagstuhl Search as Learning: summary breakout 1
 
Big Data in Learning Analytics - Analytics for Everyday Learning
Big Data in Learning Analytics - Analytics for Everyday LearningBig Data in Learning Analytics - Analytics for Everyday Learning
Big Data in Learning Analytics - Analytics for Everyday Learning
 
How to give a good 10min presentation
How to give a good 10min presentation How to give a good 10min presentation
How to give a good 10min presentation
 

Similar to 2015 hypertext-election prediction

Are Twitter Users Equal in Predicting Elections
Are Twitter Users Equal in Predicting ElectionsAre Twitter Users Equal in Predicting Elections
Are Twitter Users Equal in Predicting ElectionsLu Chen
 
Twitter Based Outcome Predictions of 2019 Indian General Elections Using Deci...
Twitter Based Outcome Predictions of 2019 Indian General Elections Using Deci...Twitter Based Outcome Predictions of 2019 Indian General Elections Using Deci...
Twitter Based Outcome Predictions of 2019 Indian General Elections Using Deci...Ferdin Joe John Joseph PhD
 
Twitter Based Election Prediction and Analysis
Twitter Based Election Prediction and AnalysisTwitter Based Election Prediction and Analysis
Twitter Based Election Prediction and AnalysisIRJET Journal
 
Turbo vote for netroots
Turbo vote for netroots Turbo vote for netroots
Turbo vote for netroots Adrienne Lever
 
2012 Presidential Elections on Twitter - An Analysis of How the US and French...
2012 Presidential Elections on Twitter - An Analysis of How the US and French...2012 Presidential Elections on Twitter - An Analysis of How the US and French...
2012 Presidential Elections on Twitter - An Analysis of How the US and French...University Politehnica Bucharest
 
Elections 2.0 - Digital Media for Elections
Elections 2.0 - Digital Media for ElectionsElections 2.0 - Digital Media for Elections
Elections 2.0 - Digital Media for Electionsadverteaze.com
 
Are Twitter Users Equal in Predicting Elections? Insights from Republican Pri...
Are Twitter Users Equal in Predicting Elections? Insights from Republican Pri...Are Twitter Users Equal in Predicting Elections? Insights from Republican Pri...
Are Twitter Users Equal in Predicting Elections? Insights from Republican Pri...Artificial Intelligence Institute at UofSC
 
Social Media @Home and @Work: Understanding Who Is Using and Why
Social Media @Home and @Work:Understanding Who Is Using and WhySocial Media @Home and @Work:Understanding Who Is Using and Why
Social Media @Home and @Work: Understanding Who Is Using and WhyCaroline Dangson
 
Public Good App House: Voting Apps - 10-3-2023
Public Good App House: Voting Apps - 10-3-2023Public Good App House: Voting Apps - 10-3-2023
Public Good App House: Voting Apps - 10-3-2023TechSoup
 
RealityMine Presentation to CIMM January 2015
RealityMine Presentation to CIMM January 2015RealityMine Presentation to CIMM January 2015
RealityMine Presentation to CIMM January 2015Rolfe William Swinton
 
Nigeria's February 14 elections : Popular opinions and attitudes
Nigeria's February 14 elections : Popular opinions and attitudesNigeria's February 14 elections : Popular opinions and attitudes
Nigeria's February 14 elections : Popular opinions and attitudesAfrobarometer
 
ОПРОС: КТО ПОБЕДИТ ТРАМПА НА СЛЕДУЮЩИХ ВЫБОРАХ
ОПРОС: КТО ПОБЕДИТ ТРАМПА НА СЛЕДУЮЩИХ ВЫБОРАХОПРОС: КТО ПОБЕДИТ ТРАМПА НА СЛЕДУЮЩИХ ВЫБОРАХ
ОПРОС: КТО ПОБЕДИТ ТРАМПА НА СЛЕДУЮЩИХ ВЫБОРАХmResearcher
 
Reuters/Ipsos Core Political: Coronavirus Tracker (05/13/2020)
Reuters/Ipsos Core Political: Coronavirus Tracker (05/13/2020)Reuters/Ipsos Core Political: Coronavirus Tracker (05/13/2020)
Reuters/Ipsos Core Political: Coronavirus Tracker (05/13/2020)Ipsos Public Affairs
 
Reuters/Ipsos Core Political Survey: Presidential Approval Tracker (08/12/2020)
Reuters/Ipsos Core Political Survey: Presidential Approval Tracker (08/12/2020)Reuters/Ipsos Core Political Survey: Presidential Approval Tracker (08/12/2020)
Reuters/Ipsos Core Political Survey: Presidential Approval Tracker (08/12/2020)Ipsos Public Affairs
 
G2 Analytics- Smarter Insights. Superior Targeting
G2 Analytics- Smarter Insights. Superior Targeting G2 Analytics- Smarter Insights. Superior Targeting
G2 Analytics- Smarter Insights. Superior Targeting G2 Analytics
 
Fingerprint Based E Voting System
Fingerprint Based E Voting SystemFingerprint Based E Voting System
Fingerprint Based E Voting Systemijtsrd
 
Reuters/Ipsos Core Political: Coronavirus Tracker (06/03/2020)
Reuters/Ipsos Core Political: Coronavirus Tracker (06/03/2020)Reuters/Ipsos Core Political: Coronavirus Tracker (06/03/2020)
Reuters/Ipsos Core Political: Coronavirus Tracker (06/03/2020)Ipsos Public Affairs
 
Australian Political Parties and social media: uses and attitudes
Australian Political Parties and social media: uses and attitudesAustralian Political Parties and social media: uses and attitudes
Australian Political Parties and social media: uses and attitudesStephen Dann
 

Similar to 2015 hypertext-election prediction (20)

Are Twitter Users Equal in Predicting Elections
Are Twitter Users Equal in Predicting ElectionsAre Twitter Users Equal in Predicting Elections
Are Twitter Users Equal in Predicting Elections
 
Twitter Based Outcome Predictions of 2019 Indian General Elections Using Deci...
Twitter Based Outcome Predictions of 2019 Indian General Elections Using Deci...Twitter Based Outcome Predictions of 2019 Indian General Elections Using Deci...
Twitter Based Outcome Predictions of 2019 Indian General Elections Using Deci...
 
Twitter Based Election Prediction and Analysis
Twitter Based Election Prediction and AnalysisTwitter Based Election Prediction and Analysis
Twitter Based Election Prediction and Analysis
 
Turbo vote for netroots
Turbo vote for netroots Turbo vote for netroots
Turbo vote for netroots
 
2012 Presidential Elections on Twitter - An Analysis of How the US and French...
2012 Presidential Elections on Twitter - An Analysis of How the US and French...2012 Presidential Elections on Twitter - An Analysis of How the US and French...
2012 Presidential Elections on Twitter - An Analysis of How the US and French...
 
Elections 2.0 - Digital Media for Elections
Elections 2.0 - Digital Media for ElectionsElections 2.0 - Digital Media for Elections
Elections 2.0 - Digital Media for Elections
 
Are Twitter Users Equal in Predicting Elections? Insights from Republican Pri...
Are Twitter Users Equal in Predicting Elections? Insights from Republican Pri...Are Twitter Users Equal in Predicting Elections? Insights from Republican Pri...
Are Twitter Users Equal in Predicting Elections? Insights from Republican Pri...
 
Social Media @Home and @Work: Understanding Who Is Using and Why
Social Media @Home and @Work:Understanding Who Is Using and WhySocial Media @Home and @Work:Understanding Who Is Using and Why
Social Media @Home and @Work: Understanding Who Is Using and Why
 
Public Good App House: Voting Apps - 10-3-2023
Public Good App House: Voting Apps - 10-3-2023Public Good App House: Voting Apps - 10-3-2023
Public Good App House: Voting Apps - 10-3-2023
 
RealityMine Presentation to CIMM January 2015
RealityMine Presentation to CIMM January 2015RealityMine Presentation to CIMM January 2015
RealityMine Presentation to CIMM January 2015
 
Social messenger
Social messengerSocial messenger
Social messenger
 
Nigeria's February 14 elections : Popular opinions and attitudes
Nigeria's February 14 elections : Popular opinions and attitudesNigeria's February 14 elections : Popular opinions and attitudes
Nigeria's February 14 elections : Popular opinions and attitudes
 
ОПРОС: КТО ПОБЕДИТ ТРАМПА НА СЛЕДУЮЩИХ ВЫБОРАХ
ОПРОС: КТО ПОБЕДИТ ТРАМПА НА СЛЕДУЮЩИХ ВЫБОРАХОПРОС: КТО ПОБЕДИТ ТРАМПА НА СЛЕДУЮЩИХ ВЫБОРАХ
ОПРОС: КТО ПОБЕДИТ ТРАМПА НА СЛЕДУЮЩИХ ВЫБОРАХ
 
Reuters/Ipsos Core Political: Coronavirus Tracker (05/13/2020)
Reuters/Ipsos Core Political: Coronavirus Tracker (05/13/2020)Reuters/Ipsos Core Political: Coronavirus Tracker (05/13/2020)
Reuters/Ipsos Core Political: Coronavirus Tracker (05/13/2020)
 
Writing A Field Plan Part 1
Writing A Field Plan Part 1Writing A Field Plan Part 1
Writing A Field Plan Part 1
 
Reuters/Ipsos Core Political Survey: Presidential Approval Tracker (08/12/2020)
Reuters/Ipsos Core Political Survey: Presidential Approval Tracker (08/12/2020)Reuters/Ipsos Core Political Survey: Presidential Approval Tracker (08/12/2020)
Reuters/Ipsos Core Political Survey: Presidential Approval Tracker (08/12/2020)
 
G2 Analytics- Smarter Insights. Superior Targeting
G2 Analytics- Smarter Insights. Superior Targeting G2 Analytics- Smarter Insights. Superior Targeting
G2 Analytics- Smarter Insights. Superior Targeting
 
Fingerprint Based E Voting System
Fingerprint Based E Voting SystemFingerprint Based E Voting System
Fingerprint Based E Voting System
 
Reuters/Ipsos Core Political: Coronavirus Tracker (06/03/2020)
Reuters/Ipsos Core Political: Coronavirus Tracker (06/03/2020)Reuters/Ipsos Core Political: Coronavirus Tracker (06/03/2020)
Reuters/Ipsos Core Political: Coronavirus Tracker (06/03/2020)
 
Australian Political Parties and social media: uses and attitudes
Australian Political Parties and social media: uses and attitudesAustralian Political Parties and social media: uses and attitudes
Australian Political Parties and social media: uses and attitudes
 

Recently uploaded

Top Call Girls In Charbagh ( Lucknow ) 🔝 8923113531 🔝 Cash Payment
Top Call Girls In Charbagh ( Lucknow  ) 🔝 8923113531 🔝  Cash PaymentTop Call Girls In Charbagh ( Lucknow  ) 🔝 8923113531 🔝  Cash Payment
Top Call Girls In Charbagh ( Lucknow ) 🔝 8923113531 🔝 Cash Paymentanilsa9823
 
Call Girls In Noida Mall Of Noida O9654467111 Escorts Serviec
Call Girls In Noida Mall Of Noida O9654467111 Escorts ServiecCall Girls In Noida Mall Of Noida O9654467111 Escorts Serviec
Call Girls In Noida Mall Of Noida O9654467111 Escorts ServiecSapana Sha
 
Top Call Girls In Telibagh ( Lucknow ) 🔝 8923113531 🔝 Cash Payment
Top Call Girls In Telibagh ( Lucknow  ) 🔝 8923113531 🔝  Cash PaymentTop Call Girls In Telibagh ( Lucknow  ) 🔝 8923113531 🔝  Cash Payment
Top Call Girls In Telibagh ( Lucknow ) 🔝 8923113531 🔝 Cash Paymentanilsa9823
 
Stunning ➥8448380779▻ Call Girls In Paharganj Delhi NCR
Stunning ➥8448380779▻ Call Girls In Paharganj Delhi NCRStunning ➥8448380779▻ Call Girls In Paharganj Delhi NCR
Stunning ➥8448380779▻ Call Girls In Paharganj Delhi NCRDelhi Call girls
 
Film the city investagation powerpoint :)
Film the city investagation powerpoint :)Film the city investagation powerpoint :)
Film the city investagation powerpoint :)AshtonCains
 
Film show production powerpoint for site
Film show production powerpoint for siteFilm show production powerpoint for site
Film show production powerpoint for siteAshtonCains
 
Call Girls In Andheri East Call 9167673311 Book Hot And Sexy Girls
Call Girls In Andheri East Call 9167673311 Book Hot And Sexy GirlsCall Girls In Andheri East Call 9167673311 Book Hot And Sexy Girls
Call Girls In Andheri East Call 9167673311 Book Hot And Sexy GirlsPooja Nehwal
 
This is a Powerpoint about research into the codes and conventions of a film ...
This is a Powerpoint about research into the codes and conventions of a film ...This is a Powerpoint about research into the codes and conventions of a film ...
This is a Powerpoint about research into the codes and conventions of a film ...samuelcoulson30
 
Ready to get noticed? Partner with Sociocosmos
Ready to get noticed? Partner with SociocosmosReady to get noticed? Partner with Sociocosmos
Ready to get noticed? Partner with SociocosmosSocioCosmos
 
GREAT OPORTUNITY Russian Call Girls Kirti Nagar 9711199012 Independent Escort...
GREAT OPORTUNITY Russian Call Girls Kirti Nagar 9711199012 Independent Escort...GREAT OPORTUNITY Russian Call Girls Kirti Nagar 9711199012 Independent Escort...
GREAT OPORTUNITY Russian Call Girls Kirti Nagar 9711199012 Independent Escort...Mona Rathore
 
CASH PAYMENT ON GIRL HAND TO HAND HOUSEWIFE
CASH PAYMENT ON GIRL HAND TO HAND HOUSEWIFECASH PAYMENT ON GIRL HAND TO HAND HOUSEWIFE
CASH PAYMENT ON GIRL HAND TO HAND HOUSEWIFECall girl Jaipur
 
Night 7k Call Girls Atta Market Escorts Call Me: 8448380779
Night 7k Call Girls Atta Market Escorts Call Me: 8448380779Night 7k Call Girls Atta Market Escorts Call Me: 8448380779
Night 7k Call Girls Atta Market Escorts Call Me: 8448380779Delhi Call girls
 
Call Girls In South Ex. Delhi O9654467111 Women Seeking Men
Call Girls In South Ex. Delhi O9654467111 Women Seeking MenCall Girls In South Ex. Delhi O9654467111 Women Seeking Men
Call Girls In South Ex. Delhi O9654467111 Women Seeking MenSapana Sha
 
Spotify AI DJ Deck - The Agency at University of Florida
Spotify AI DJ Deck - The Agency at University of FloridaSpotify AI DJ Deck - The Agency at University of Florida
Spotify AI DJ Deck - The Agency at University of Floridajorirz24
 
Film show pre-production powerpoint for site
Film show pre-production powerpoint for siteFilm show pre-production powerpoint for site
Film show pre-production powerpoint for siteAshtonCains
 
c Starting with 5000/- for Savita Escorts Service 👩🏽‍❤️‍💋‍👨🏿 8923113531 ♢ Boo...
c Starting with 5000/- for Savita Escorts Service 👩🏽‍❤️‍💋‍👨🏿 8923113531 ♢ Boo...c Starting with 5000/- for Savita Escorts Service 👩🏽‍❤️‍💋‍👨🏿 8923113531 ♢ Boo...
c Starting with 5000/- for Savita Escorts Service 👩🏽‍❤️‍💋‍👨🏿 8923113531 ♢ Boo...gurkirankumar98700
 
Film show investigation powerpoint for the site
Film show investigation powerpoint for the siteFilm show investigation powerpoint for the site
Film show investigation powerpoint for the siteAshtonCains
 
Unlock the power of Instagram with SocioCosmos. Start your journey towards so...
Unlock the power of Instagram with SocioCosmos. Start your journey towards so...Unlock the power of Instagram with SocioCosmos. Start your journey towards so...
Unlock the power of Instagram with SocioCosmos. Start your journey towards so...SocioCosmos
 
O9654467111 Call Girls In Dwarka Women Seeking Men
O9654467111 Call Girls In Dwarka Women Seeking MenO9654467111 Call Girls In Dwarka Women Seeking Men
O9654467111 Call Girls In Dwarka Women Seeking MenSapana Sha
 

Recently uploaded (20)

Top Call Girls In Charbagh ( Lucknow ) 🔝 8923113531 🔝 Cash Payment
Top Call Girls In Charbagh ( Lucknow  ) 🔝 8923113531 🔝  Cash PaymentTop Call Girls In Charbagh ( Lucknow  ) 🔝 8923113531 🔝  Cash Payment
Top Call Girls In Charbagh ( Lucknow ) 🔝 8923113531 🔝 Cash Payment
 
Call Girls In Noida Mall Of Noida O9654467111 Escorts Serviec
Call Girls In Noida Mall Of Noida O9654467111 Escorts ServiecCall Girls In Noida Mall Of Noida O9654467111 Escorts Serviec
Call Girls In Noida Mall Of Noida O9654467111 Escorts Serviec
 
Top Call Girls In Telibagh ( Lucknow ) 🔝 8923113531 🔝 Cash Payment
Top Call Girls In Telibagh ( Lucknow  ) 🔝 8923113531 🔝  Cash PaymentTop Call Girls In Telibagh ( Lucknow  ) 🔝 8923113531 🔝  Cash Payment
Top Call Girls In Telibagh ( Lucknow ) 🔝 8923113531 🔝 Cash Payment
 
Stunning ➥8448380779▻ Call Girls In Paharganj Delhi NCR
Stunning ➥8448380779▻ Call Girls In Paharganj Delhi NCRStunning ➥8448380779▻ Call Girls In Paharganj Delhi NCR
Stunning ➥8448380779▻ Call Girls In Paharganj Delhi NCR
 
Film the city investagation powerpoint :)
Film the city investagation powerpoint :)Film the city investagation powerpoint :)
Film the city investagation powerpoint :)
 
Film show production powerpoint for site
Film show production powerpoint for siteFilm show production powerpoint for site
Film show production powerpoint for site
 
Call Girls In Andheri East Call 9167673311 Book Hot And Sexy Girls
Call Girls In Andheri East Call 9167673311 Book Hot And Sexy GirlsCall Girls In Andheri East Call 9167673311 Book Hot And Sexy Girls
Call Girls In Andheri East Call 9167673311 Book Hot And Sexy Girls
 
This is a Powerpoint about research into the codes and conventions of a film ...
This is a Powerpoint about research into the codes and conventions of a film ...This is a Powerpoint about research into the codes and conventions of a film ...
This is a Powerpoint about research into the codes and conventions of a film ...
 
Ready to get noticed? Partner with Sociocosmos
Ready to get noticed? Partner with SociocosmosReady to get noticed? Partner with Sociocosmos
Ready to get noticed? Partner with Sociocosmos
 
GREAT OPORTUNITY Russian Call Girls Kirti Nagar 9711199012 Independent Escort...
GREAT OPORTUNITY Russian Call Girls Kirti Nagar 9711199012 Independent Escort...GREAT OPORTUNITY Russian Call Girls Kirti Nagar 9711199012 Independent Escort...
GREAT OPORTUNITY Russian Call Girls Kirti Nagar 9711199012 Independent Escort...
 
CASH PAYMENT ON GIRL HAND TO HAND HOUSEWIFE
CASH PAYMENT ON GIRL HAND TO HAND HOUSEWIFECASH PAYMENT ON GIRL HAND TO HAND HOUSEWIFE
CASH PAYMENT ON GIRL HAND TO HAND HOUSEWIFE
 
Night 7k Call Girls Atta Market Escorts Call Me: 8448380779
Night 7k Call Girls Atta Market Escorts Call Me: 8448380779Night 7k Call Girls Atta Market Escorts Call Me: 8448380779
Night 7k Call Girls Atta Market Escorts Call Me: 8448380779
 
Call Girls In South Ex. Delhi O9654467111 Women Seeking Men
Call Girls In South Ex. Delhi O9654467111 Women Seeking MenCall Girls In South Ex. Delhi O9654467111 Women Seeking Men
Call Girls In South Ex. Delhi O9654467111 Women Seeking Men
 
Spotify AI DJ Deck - The Agency at University of Florida
Spotify AI DJ Deck - The Agency at University of FloridaSpotify AI DJ Deck - The Agency at University of Florida
Spotify AI DJ Deck - The Agency at University of Florida
 
Film show pre-production powerpoint for site
Film show pre-production powerpoint for siteFilm show pre-production powerpoint for site
Film show pre-production powerpoint for site
 
c Starting with 5000/- for Savita Escorts Service 👩🏽‍❤️‍💋‍👨🏿 8923113531 ♢ Boo...
c Starting with 5000/- for Savita Escorts Service 👩🏽‍❤️‍💋‍👨🏿 8923113531 ♢ Boo...c Starting with 5000/- for Savita Escorts Service 👩🏽‍❤️‍💋‍👨🏿 8923113531 ♢ Boo...
c Starting with 5000/- for Savita Escorts Service 👩🏽‍❤️‍💋‍👨🏿 8923113531 ♢ Boo...
 
Film show investigation powerpoint for the site
Film show investigation powerpoint for the siteFilm show investigation powerpoint for the site
Film show investigation powerpoint for the site
 
Unlock the power of Instagram with SocioCosmos. Start your journey towards so...
Unlock the power of Instagram with SocioCosmos. Start your journey towards so...Unlock the power of Instagram with SocioCosmos. Start your journey towards so...
Unlock the power of Instagram with SocioCosmos. Start your journey towards so...
 
O9654467111 Call Girls In Dwarka Women Seeking Men
O9654467111 Call Girls In Dwarka Women Seeking MenO9654467111 Call Girls In Dwarka Women Seeking Men
O9654467111 Call Girls In Dwarka Women Seeking Men
 
🔝9953056974 🔝Call Girls In Mehrauli Escort Service Delhi NCR
🔝9953056974 🔝Call Girls In Mehrauli  Escort Service Delhi NCR🔝9953056974 🔝Call Girls In Mehrauli  Escort Service Delhi NCR
🔝9953056974 🔝Call Girls In Mehrauli Escort Service Delhi NCR
 

2015 hypertext-election prediction

  • 1. Twitter-based election prediction in the developing world Nugroho Dwi Prasetyo & Claudia Hauff
  • 2. Twitter-based election polling is a cheap alternative to traditional “offline” polls. Twitter-based election polling should achieve a prediction accuracy similar to traditional polls. millions of potential voters inferred votes biases The what & why
  • 3. @flickr:misteraitch “No, you cannot predict elections with Twitter.” D. Gayo-Avello. Internet Computing, IEEE 16.6 (2012): 91-94.
  • 4. @flickr:misteraitch “No, you cannot predict elections with Twitter.” D. Gayo-Avello. Internet Computing, IEEE 16.6 (2012): 91-94. That hasn’t stopped people from trying!
  • 5. @flickr:practicalowl Germany Federal Count tweets & hashtags 5 weeks6 party names 1.7% Singapore Presidential Count tweets + sentiment 1 week4 candidate names 6.1% USA Presidential Count tweets + sentiment 6 months2 candidate names 11.6% Ireland General Count tweets + sentiment 3 weeks5 party names + election hashtag 3-6% Netherlands Senate Count tweets 1 month12 Dutch words 1.3% USA Presidential Count tweets 6 weeks2 N/A 1.7% Germany Federal Count hashtags + sentiment 4 months6 party names + election hashtags N/A USA, France Presidential sentiment 2 months2 candidate names + election hashtag N/A USA Republican nomination Count tweets + sentiment 1 year7 candidate names N/A Venezuela, Paraguay, Ecuador Presidential Count tweets + users 7 months 2 3 2 candidate names and aliases 0.1%- 19%
  • 6. So far … Twitter-based predictions lack behind traditional polls. Most works focus on elections in the developed world. Traditional polls are accurate. Traditional polls are conducted often.
  • 7. So far … Twitter-based predictions lack behind traditional polls. Most works focus on elections in the developed world. What do Twitter-based methods add?
  • 8. In the developing world … traditional polls are less likely to be reliable. … the demographic bias of Twitter users is high. 4.08% 3.45%11.75% 4.21% 12.24% 5.64% 6.25% 1.36% 2.69% 1.19% 7.02% 4.20% 8.84% 0.98% 3.96% 3.13% 4.24%1.15% 0.87% 11.49% Mean Absolute Error of 20 traditional polls conducted in the run-up to the 2014 Indonesian presidential election
  • 9. A detailed analysis of all major factors of Twitter-based election forecasting with a special emphasis on de- biasing through “offline” data. An in-depth comparison of 20 traditional polls and Twitter-based forecasts for the 2014 Indonesian presidential election. Our contributions @flickr:carbonnyc
  • 11. Processing pipeline (1) Data collection election type data access duration keywords (3) Data de-biasing age gender location (2) Data filtering spam organisations geo-location (4) Election prediction candidate mentions one vote per user tweet sentiment
  • 12. The ground truth election outcome & traditional polls predicted vote % election vote %#candidates
  • 14. 2014 Indonesian 
 presidential election Joko Widodo vs. Prabowo Subianto Widodo won 53.15% of the votes. Widodo won in 23 of the 33 provinces. Widodo was supported by the opposition. July 9, 2014
  • 15. Gathered tweets Crawling period #Electoral tweets Max. tweets / day #Users Max. active users / day April 15 - July 8, 2014 7,020,228 375,064 490,270 148,135 Manually curated keyword list (updated daily); only tweets geo-located in Indonesia are included. POLLDATA
  • 16. Gathered tweets II #Users Most recent 100 tweets per user. Not used for prediction purposes. USERDATA Crawling period July 25 - 30, 2014 #Tweets ~42,000,000 490,270
  • 18. Is spam a problem? 7.4% are spam users 2.1% are “slacktivists” 3.8% are non-personal users Based on a manual classification of 600 randomly selected users in USERDATA
  • 19. How large is the bias? Based on a manual classification of 600 randomly selected users in USERDATA 0% 20% 40% 60% 80% Female Male Twitter Population gender 0% 20% 40% 60% 80% 0-19 20-49 50+ Twitter Population age
  • 20. How large is the bias? 0% 20% 40% 60% 80% Female Male Twitter Population gender 0% 20% 40% 60% 80% 0-19 20-49 50+ Twitter Population age Automatic classification of POLLDATA. age gender
  • 21. How large is the bias? Based on reserve geo-coding & population data for Indonesia. location Jakarta Internet penetration rate: 17% location
  • 23. From tweets to users tweet count 56.45% 3.3% +7 23/3343.55% -13 0.27 W idodo Subianto MAE traditional polls province level correct min. MAE 26.09 max. MAE user count 54.45% 1.3% +4 24/3345.55% -16 0.05 25.01 On the national level, “one user one vote” outperforms tweet-based predictions (confirming prior works). On the province level the changes are miniscule. our baselines
  • 24. Keyword selection all keywords candidate name 5 keywords Simply using more keywords does not always lead to better results.
  • 25. Location de-biasing tweet count 55.14% 2.0% +544.86% -15 W idodo Subianto MAE traditional polls user count 54.26% 1.1% +245.74% -18 Decreasing the influence of tweets from overrepresented locations in the dataset improves the prediction.
  • 26. Gender de-biasing tweet count 56.36% 3.2% +7 21/3343.64% -13 0.33 W idodo Subianto MAE traditional polls province level correct min. MAE 28.05 max. MAE user count 54.89% 1.7% +5 23/3345.11% -15 0.10 26.72 Correcting for gender biases degrades the prediction accuracy on the national & province level.
  • 27. Impact of sentiment tweet count 53.98% 0.8% +046.02% -20 W idodo Subianto MAE traditional polls province level correct min. MAE max. MAE user count 54.02% 0.9% +045.98% -20 On the national level, sentiment yields the best forecast. tweet count 50.67% 2.5% +549.33% -15 user count 53.77% 0.6% +046.23% -20 14/33 0.01 54.90 19/33 0.26 26.51 14/33 0.01 49.79 19/33 0.01 26.40 POSPOS+NEG The impact on the province level prediction is negative.
  • 28. Impact of sentiment tweet count 53.98% 0.8% +046.02% -20 W idodo Subianto MAE traditional polls province level correct min. MAE max. MAE user count 54.02% 0.9% +045.98% -20 On the national level, sentiment yields the best forecast. tweet count 50.67% 2.5% +549.33% -15 user count 53.77% 0.6% +046.23% -20 14/33 0.01 54.90 19/33 0.26 26.51 14/33 0.01 49.79 19/33 0.01 26.40 POSPOS+NEG The impact on the province level prediction is negative. More than 700 languages are spoken in Indonesia
  • 29. Conclusions Simple Twitter-based predictors outperform (almost) all traditional polls in Indonesia. Accurate predictions on province level are challenging, due to data sparsity & data diversity. Currently: designing a Web application prototype to automatically observe ongoing elections.