coletto, lucchese, orlando, perego electoral predictions with twitter: a machine-learning approach...
TRANSCRIPT
![Page 1: Coletto, Lucchese, Orlando, Perego ELECTORAL PREDICTIONS WITH TWITTER: A MACHINE-LEARNING APPROACH M. Coletto 1,3, C. Lucchese 1, S. Orlando 2, and R](https://reader030.vdocuments.us/reader030/viewer/2022033103/56649db95503460f94aa971b/html5/thumbnails/1.jpg)
Coletto, Lucchese, Orlando, Perego
Electoral Predictions with Twitter: a Machine-Learning approach
M. Coletto1,3, C. Lucchese1, S. Orlando2, and R. Perego1
1 ISTI-CNR, Pisa2 University Ca’ Foscari of Venice3 IMT Institute for Advanced Studies, Lucca
May 2015
![Page 2: Coletto, Lucchese, Orlando, Perego ELECTORAL PREDICTIONS WITH TWITTER: A MACHINE-LEARNING APPROACH M. Coletto 1,3, C. Lucchese 1, S. Orlando 2, and R](https://reader030.vdocuments.us/reader030/viewer/2022033103/56649db95503460f94aa971b/html5/thumbnails/2.jpg)
Coletto, Lucchese, Orlando, Perego
In this work we study how Twitter can provide some interesting insights concerning the primary elections of an Italian political party.
INTRODUCTION
26/05/15 2
![Page 3: Coletto, Lucchese, Orlando, Perego ELECTORAL PREDICTIONS WITH TWITTER: A MACHINE-LEARNING APPROACH M. Coletto 1,3, C. Lucchese 1, S. Orlando 2, and R](https://reader030.vdocuments.us/reader030/viewer/2022033103/56649db95503460f94aa971b/html5/thumbnails/3.jpg)
Coletto, Lucchese, Orlando, Perego
• STATE-OF-THE-ART• DATA• BASELINE• METHODS• AGE BIAS• CONCLUSION
AGENDA
26/05/15 3
![Page 4: Coletto, Lucchese, Orlando, Perego ELECTORAL PREDICTIONS WITH TWITTER: A MACHINE-LEARNING APPROACH M. Coletto 1,3, C. Lucchese 1, S. Orlando 2, and R](https://reader030.vdocuments.us/reader030/viewer/2022033103/56649db95503460f94aa971b/html5/thumbnails/4.jpg)
Coletto, Lucchese, Orlando, Perego
Twitter for predictive tasks: from prediction of stock market [1] to movie sales [2], and pandemics detection [3].
Many articles propose quantitative approaches to predict the electoral results in different countries: US [4], Germany [5], Holland [6], Italy [7].
STATE-OF-THE-ART
[1] Bollen, J., Mao, H., Zeng, X.: Twitter mood predicts the stock market. Journal of Computa- tional Science 2(1), 1–8 (2011) [2] Asur, S., Huberman, B.A.: Predicting the future with social media. In: Web Intelligence and Intelligent Agent Technology (WI-IAT), 2010 IEEE/WIC/ACM International Conference on. vol. 1, pp. 492–499. IEEE (2010) [3] Lampos, V., De Bie, T., Cristianini, N.: Flu detector-tracking epidemics on twitter. In: Ma- chine Learning and Knowledge Discovery in Databases, pp. 599–602. Springer (2010) [4] O’Connor, B., Balasubramanyan, R., Routledge, B.R., Smith, N.A.: From tweets to polls: Linking text sentiment to public opinion time series. ICWSM 11, 122–129 (2010) [5] Tumasjan, A., Sprenger, T.O., Sandner, P.G., Welpe, I.M.: Predicting elections with twitter: What 140 characters reveal about political sentiment. ICWSM 10, 178–185 (2010) [6] Sang, E.T.K., Bos, J.: Predicting the 2011 dutch senate election results with twit- ter. In: Proceedings of the Workshop on Semantic Analysis in Social Media. pp. 53–60. Association for Computational Linguistics, Stroudsburg, PA, USA (2012) [7] Caldarelli,G.,Chessa,A.,Pammolli,F.,Pompa,G.,Puliga,M.,Riccaboni,M.,Riotta,G.:A multi-level geographical study of italian political elections from twitter data. PloS one 9(5), e95809 (2014) 26/05/15 4
![Page 5: Coletto, Lucchese, Orlando, Perego ELECTORAL PREDICTIONS WITH TWITTER: A MACHINE-LEARNING APPROACH M. Coletto 1,3, C. Lucchese 1, S. Orlando 2, and R](https://reader030.vdocuments.us/reader030/viewer/2022033103/56649db95503460f94aa971b/html5/thumbnails/5.jpg)
Coletto, Lucchese, Orlando, Perego26/05/15 5
![Page 6: Coletto, Lucchese, Orlando, Perego ELECTORAL PREDICTIONS WITH TWITTER: A MACHINE-LEARNING APPROACH M. Coletto 1,3, C. Lucchese 1, S. Orlando 2, and R](https://reader030.vdocuments.us/reader030/viewer/2022033103/56649db95503460f94aa971b/html5/thumbnails/6.jpg)
Coletto, Lucchese, Orlando, Perego
DATA
26/05/15 6
![Page 7: Coletto, Lucchese, Orlando, Perego ELECTORAL PREDICTIONS WITH TWITTER: A MACHINE-LEARNING APPROACH M. Coletto 1,3, C. Lucchese 1, S. Orlando 2, and R](https://reader030.vdocuments.us/reader030/viewer/2022033103/56649db95503460f94aa971b/html5/thumbnails/7.jpg)
Coletto, Lucchese, Orlando, Perego26/05/15 7
![Page 8: Coletto, Lucchese, Orlando, Perego ELECTORAL PREDICTIONS WITH TWITTER: A MACHINE-LEARNING APPROACH M. Coletto 1,3, C. Lucchese 1, S. Orlando 2, and R](https://reader030.vdocuments.us/reader030/viewer/2022033103/56649db95503460f94aa971b/html5/thumbnails/8.jpg)
Coletto, Lucchese, Orlando, Perego
Tumasjan, A., Sprenger, T.O., Sandner, P.G., Welpe, I.M.: Predicting elections with twitter: What 140 characters reveal about political sentiment. ICWSM 10, 178–185 (2010)
TweetCount
DiGrazia, J., McKelvey, K., Bollen, J., Rojas, F.: More tweets, more votes: Social media as a quantitative indicator of political behavior. PloS one 8(11), e79449 (2013)
UserCount
BASELINE
26/05/15 8
![Page 9: Coletto, Lucchese, Orlando, Perego ELECTORAL PREDICTIONS WITH TWITTER: A MACHINE-LEARNING APPROACH M. Coletto 1,3, C. Lucchese 1, S. Orlando 2, and R](https://reader030.vdocuments.us/reader030/viewer/2022033103/56649db95503460f94aa971b/html5/thumbnails/9.jpg)
Coletto, Lucchese, Orlando, Perego
• EVALUATION:- MAE(mean absolute error)- RMSE (root-mean-square error)- MRM(mean rank match)
26/05/15 9
![Page 10: Coletto, Lucchese, Orlando, Perego ELECTORAL PREDICTIONS WITH TWITTER: A MACHINE-LEARNING APPROACH M. Coletto 1,3, C. Lucchese 1, S. Orlando 2, and R](https://reader030.vdocuments.us/reader030/viewer/2022033103/56649db95503460f94aa971b/html5/thumbnails/10.jpg)
Coletto, Lucchese, Orlando, Perego
Proposed classification methods-UserShare
-ClassTweetCount
-ClassUserCount
METHODS
26/05/15 10
![Page 11: Coletto, Lucchese, Orlando, Perego ELECTORAL PREDICTIONS WITH TWITTER: A MACHINE-LEARNING APPROACH M. Coletto 1,3, C. Lucchese 1, S. Orlando 2, and R](https://reader030.vdocuments.us/reader030/viewer/2022033103/56649db95503460f94aa971b/html5/thumbnails/11.jpg)
Coletto, Lucchese, Orlando, Perego26/05/15 11
![Page 12: Coletto, Lucchese, Orlando, Perego ELECTORAL PREDICTIONS WITH TWITTER: A MACHINE-LEARNING APPROACH M. Coletto 1,3, C. Lucchese 1, S. Orlando 2, and R](https://reader030.vdocuments.us/reader030/viewer/2022033103/56649db95503460f94aa971b/html5/thumbnails/12.jpg)
Coletto, Lucchese, Orlando, Perego
• Training correcting factors through ML– Per candidate– Learning weights to evaluate Twitter
user/ voters ratio– Metrics: UserShare, ClassTweetCount
• Content Analysis (100 most frequent hash-tags)– 1 feature per word– Sentiment Analysis per candidate
METHODS 2
26/05/15 12
![Page 13: Coletto, Lucchese, Orlando, Perego ELECTORAL PREDICTIONS WITH TWITTER: A MACHINE-LEARNING APPROACH M. Coletto 1,3, C. Lucchese 1, S. Orlando 2, and R](https://reader030.vdocuments.us/reader030/viewer/2022033103/56649db95503460f94aa971b/html5/thumbnails/13.jpg)
Coletto, Lucchese, Orlando, Perego26/05/15 13
![Page 14: Coletto, Lucchese, Orlando, Perego ELECTORAL PREDICTIONS WITH TWITTER: A MACHINE-LEARNING APPROACH M. Coletto 1,3, C. Lucchese 1, S. Orlando 2, and R](https://reader030.vdocuments.us/reader030/viewer/2022033103/56649db95503460f94aa971b/html5/thumbnails/14.jpg)
Coletto, Lucchese, Orlando, Perego26/05/15 14
![Page 15: Coletto, Lucchese, Orlando, Perego ELECTORAL PREDICTIONS WITH TWITTER: A MACHINE-LEARNING APPROACH M. Coletto 1,3, C. Lucchese 1, S. Orlando 2, and R](https://reader030.vdocuments.us/reader030/viewer/2022033103/56649db95503460f94aa971b/html5/thumbnails/15.jpg)
Coletto, Lucchese, Orlando, Perego
AGE BIAS
26/05/15 15
![Page 16: Coletto, Lucchese, Orlando, Perego ELECTORAL PREDICTIONS WITH TWITTER: A MACHINE-LEARNING APPROACH M. Coletto 1,3, C. Lucchese 1, S. Orlando 2, and R](https://reader030.vdocuments.us/reader030/viewer/2022033103/56649db95503460f94aa971b/html5/thumbnails/16.jpg)
Coletto, Lucchese, Orlando, Perego26/05/15 16
![Page 17: Coletto, Lucchese, Orlando, Perego ELECTORAL PREDICTIONS WITH TWITTER: A MACHINE-LEARNING APPROACH M. Coletto 1,3, C. Lucchese 1, S. Orlando 2, and R](https://reader030.vdocuments.us/reader030/viewer/2022033103/56649db95503460f94aa971b/html5/thumbnails/17.jpg)
Coletto, Lucchese, Orlando, Perego
• New predictors• Machine learning approach• Age bias analysis
LIMITATIONS AND FUTURE WORK• Twitter bias• Single dataset (European)• Arbitrariness (window, keywords, ..)
CONCLUSION
26/05/15 17
![Page 18: Coletto, Lucchese, Orlando, Perego ELECTORAL PREDICTIONS WITH TWITTER: A MACHINE-LEARNING APPROACH M. Coletto 1,3, C. Lucchese 1, S. Orlando 2, and R](https://reader030.vdocuments.us/reader030/viewer/2022033103/56649db95503460f94aa971b/html5/thumbnails/18.jpg)
Coletto, Lucchese, Orlando, Perego
THANK YOU
QUESTIONS?