Abstract
In this paper, we propose a framework to infer Twitter follower preferences for the 2016 U.S. presidential primaries. Using Twitter data collected from Sept. 2015 to Mar. 2016, we first uncover the tweeting tactics of the candidates and then exploit the variations in the number of ‘likes’ to infer followers’ preference. With sparse learning, we are able to reveal neutral topics as well as positive and negative ones.
Methodologically, we are able to achieve a higher predictive power with sparse learning. Substantively, we show that for Hillary Clinton the (only) positive issue area is women’s rights. We demonstrate that Hillary Clinton’s tactic of linking herself to President Obama resonates well with her supporters but the same is not true for Bernie Sanders. In addition, we show that Donald Trump is a major topic for all the other candidates, and that the women’s rights issue is equally emphasized in Sanders’ campaign as in Clinton’s.
Lessons from the primaries can help inform the general election and beyond. We suggest two ways that politicians can use the feedback mechanism in social media to improve their campaign: (1) use feedback from social media to improve campaign tactics within social media; (2) formulate policies and test the public response from the social media.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
For example, during the Democratic debate in Flint, Michigan, a tweet by Bernie Sanders targeting Hillary Clinton became the focal point. During the eleventh Republican debate, Donald Trump explicitly invited the audience to check his Twitter account.
- 2.
We do not count retweets, because retweets do not have as a feature the number of ‘likes’ and our focus is on the number of ‘likes’ in this work.
- 3.
The selection is based on both polling results and on the number of delegates that each candidate has. Marco Rubio (R) dropped out of the race on March 15th, 2016. Throughout, we follow the convention that Republican candidates are marked with (R) and Democratic candidates are marked with (D).
- 4.
- 5.
Eleven other candidates, including John Kasich (R) and Martin O’Malley (D), are also included in the dataset.
- 6.
By the end of the New Hampshire primary, Martin O’Malley, Rand Paul, and Chris Christie have quit the race.
- 7.
The selection of political figures is based on the poll performance. For poll data, please refer to http://elections.huffingtonpost.com/pollster#2016-primaries. The selection of political issues follows the Bing Political Index. Available at https://blogs.bing.com/search/2015/12/08/the-bing-2016-election-experience-how-do-the-candidates-measure-up.
- 8.
- 9.
We calculate the derivative of L with respect to log(\(\alpha \)) instead of \(\alpha \) to ensure that \(\alpha \) stays positive throughout the optimization procedure.
- 10.
We have posted our codes at http://sites.google.com/site/wangyurochester.
- 11.
When the penalty term is zero, our results are identical to the standard outputs from Stata (http://www.stata.com) and R.
- 12.
For a review of Sanders’ rise and his proposed policies, please see http://www.nytimes.com/2016/03/13/opinion/sunday/the-bernie-sanders-revolution.html.
References
Blei, D.M., Ng, A.Y., Jordan, M.I.: Latent Dirichlet allocation. J. Mach. Learn. Res. 3, 993–1022 (2003)
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)
Efron, B., Tibshirani, R.J.: An Introduction to the Bootstrap. Chapman & Hall/CRC, New York (1993)
Gayo-Avello, D., Metaxas, P.T., Mustafaraj, E.: Limits of electoral predictions using twitter. In: Proceedings of the Fifth International AAAI Conference on Weblogs and Social Media (2011)
Greene, W.: Functional forms for the negative binomial model for count data. Econ. Lett. 99, 585–590 (2008)
Hastie, T., Tibshirani, R., Wainwright, M.: Statistical Learning with Sparsity: The Lasso and Generalizations. CRC Press, Boca Raton (2015)
Iyengar, S., Kinder, D., Matter, N.T.: Television and American Opinion. University of Chicago Press, Chicago (1987)
Lee, K., Mahmud, J., Chen, J., Zhou, M., Nichols, J.: Who will retweet this? detecting strangers from twitter to retweet information. ACM Trans. Intell. Syst. Technol. 6(3), 1–25 (2015)
Lenz, G.S., Learning, O.C., Priming, N.: Reconsidering the Priming Hypothesis. Am. J. Polit. Sci. 53, 821–837 (2009)
MacWilliams, M.C.: Forecasting congressional elections using facebook data. PS: Polit. Sci. Politics 48(04), October 2015
Mahmud, J., Chen, J., Nichols, J.: When will you answer this? estimating response time in twitter. In: Proceedings of the Seventh International AAAI Conference on Weblogs and Social Media (2013)
Riker, W.H.: The Art of Political Manipulation. Yale University Press, USA (1986)
Sanders, B., Revolution, O.: A Future to Believe In. Thomas Dunne Books (2016)
Shalev-Shwartz, S., Tewari, A.: Stochastic methods for L1-regularized loss minimization. J. Mach. Learn. Res. 12, 1865–1892 (2011)
Stata.com. Negative binomial regression
Tibshirani, R.: Regression Shrinkage and Selection via the Lasso. J. Roy. Stat. Soc. Ser. B (Methodol.) 58(1), 267–288 (1996)
Tumasjan, A., Sprenger, T.O., Sandner, P.G., Welpe, I.M.: Predicting elections with twitter: what 140 characters reveal about political sentiment. In: Proceedings of the Fourth International AAAI Conference on Weblogs and Social Media (2010)
Wang, Y., Li, Y., Luo, J.: Deciphering the 2016 U.S. presidential campaign in the twitter sphere: a comparison of the trumpists and clintonists. In: The 10th International AAAI Conference on Web and Social Media (ICWSM-16), Cologne, Germany, May 2016
Wang, Y., Li, Y., Luo, J.: To follow or not to follow: analyzing the growth patterns of the Trumpists on Twitter. In: News and Pulic Opinion Workshop at the 10th International AAAI Conference on Web and Social Media (ICWSM-16), Cologne, Germany, May 2016
Wang, Y., Luo, J., Li, Y., Hu, T.: Catching fire via ‘Likes’: inferring topic preferences of trump followers on twitter. In: The 10th International AAAI Conference on Web and Social Media (ICWSM 2016), Cologne, Germany, May 2016
Williams, C.B., Gulati, G.J.: The political impact of Facebook: evidence from the 2006 midterm elections and 2008 nomination contest. Politics Technol. Rev. 1, 11–21 (2008)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2017 Springer International Publishing AG
About this paper
Cite this paper
Wang, Y., Feng, Y., Zhang, X., Luo, J. (2017). Inferring Follower Preferences in the 2016 U.S. Presidential Primaries with Sparse Learning. In: Lee, D., Lin, YR., Osgood, N., Thomson, R. (eds) Social, Cultural, and Behavioral Modeling. SBP-BRiMS 2017. Lecture Notes in Computer Science(), vol 10354. Springer, Cham. https://doi.org/10.1007/978-3-319-60240-0_1
Download citation
DOI: https://doi.org/10.1007/978-3-319-60240-0_1
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-60239-4
Online ISBN: 978-3-319-60240-0
eBook Packages: Computer ScienceComputer Science (R0)