Abstract
Motivated by the question of how the public in an authoritarian political environment may perceive democratic elections, we analyze the underlying interests and sentiments of the Chinese audience regarding the 2016 US Presidential Election with the social media data collected from a large Chinese online community. We extract several latent topics of interest to the community from the text corpus by applying the unsupervised learning method of Latent Dirichlet Allocation (LDA), and explore the amount of interests received by each topic by applying the supervised learning methods, including the Bayesian Additive Regression Trees and the Bayesian LASSO model. Results reveal much more attentions paid by the audience to the sensational news, especially the controversies related to Hillary Clinton’s email leakage and Donald Trump’s anti-political-correctness and anti-globalization remarks, than to the substantive issues, e.g., regarding the candidates’ policy agendas or the democratic process.
We thank for kind suggestions from Joseph Chang, John Henderson and Wenhui Yang. All remaining errors are our own.
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.
To further mitigate the influence of extremely short answers, the LDA results presented are based on answers with more than ten political words (20, 637 in total). There is no substantive difference with empirical results by slightly increasing or decreasing the threshold.
- 2.
It should be noted that we use the LDA outputs instead of raw text features as the input X at the answer level (Table 2) due to the matrix sparsity and the latter’s excessively high demand for computational power.
- 3.
A more delicate variable selection procedure is described in [2], which compares the variable’s proportion rate to some thresholds obtained by permutation. This process is nevertheless computationally demanding.
- 4.
Zhihu: Use Knowledge to Connect the World (in Chinese). Xinhuanet (http://news.xinhuanet.com/newmedia/2015-05/14/c_134238843.htm). 14 May 2015. Retrieved on 15 April 2017.
- 5.
For instance,
(to advise someone earnestly) is a single-word phrase often used in ancient Chinese, and its counterparts commonly used in modern Chinese are 
or 
. - 6.
Some highly frequent English words, for instance Trump, Hillary, and LGBT, are converted to Chinese.
- 7.
How Chinese netizens call foreign politicians is less a strategy to avoid censorship than an expression of political preference. Comparatively, informal names that Chinese citizens use to call Hillary Clinton have stronger denigratory meaning in Chinese.
(to advise someone earnestly) is a single-word phrase often used in ancient Chinese, and its counterparts commonly used in modern Chinese are 
or 
.References
Blei, D.M., Ng, A.Y., Jordan, M.I.: Latent Dirichlet allocation. J. Mach. Learn. Res. 3, 993–1022 (2003)
Bleich, J., Kapelner, A., George, E.I., Jensen, S.T., et al.: Variable selection for BART: an application to gene regulation. Ann. Appl. Stat. 8(3), 1750–1781 (2014)
Chipman, H.A., George, E.I., McCulloch, R.E., et al.: BART: Bayesian Additive Regression Trees. Ann. Appl. Stat. 4(1), 266–298 (2010)
Calafiore, G.C., El Ghaoui, L., Preziosi, A., Russo, L.: Topic analysis in news via sparse learning: a case study on the 2016 US Presidential Elections. In: The 20th World Congress of International Federation of Automatic Control (2017, forthcoming)
Einstein, K.L., Glick, D.M.: Do I think BLS data are BS? The consequences of conspiracy theories. Polit. Behav. 37(3), 679–701 (2015)
Huang, H.: International knowledge and domestic evaluations in a changing society: the case of China. Am. Polit. Sci. Rev. 109(03), 613–634 (2015)
Huang, H., Yeh, Y.Y.: Information from abroad: foreign media, selective exposure, and political support in China. Br. J. Polit. Sci. (2016, forthcoming)
Imai, K., Lo, J., Olmsted, J.: Fast estimation of ideal points with massive data. Am. Polit. Sci. Rev. 110(4), 631–656 (2016)
Jolley, D., Douglas, K.M.: The social consequences of conspiracism: exposure to conspiracy theories decreases intentions to engage in politics and to reduce one’s carbon footprint. Br. J. Psychol. 105(1), 35–56 (2014)
King, G., Pan, J., Roberts, M.E.: How censorship in China allows government criticism but silences collective expression. Am. Polit. Sci. Rev. 107(02), 326–343 (2013)
Slapin, J.B., Proksch, S.O.: A scaling model for estimating time-series party positions from texts. Am. J. Polit. Sci. 52(3), 705–722 (2008)
Swami, V., Chamorro-Premuzic, T., Furnham, A.: Unanswered questions: a preliminary investigation of personality and individual difference predictors of 9/11 conspiracist beliefs. Appl. Cogn. Psychol. 24(6), 749–761 (2010)
Tibshirani, R.: Regression shrinkage and selection via the LASSO. J. Roy. Stat. Soc. Ser. B (Methodol.) 58, 267–288 (1996)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2017 Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Yue, J., Li, Y., Sundquist, J. (2017). The 2016 US Presidential Election and Its Chinese Audience. In: Cheng, X., Ma, W., Liu, H., Shen, H., Feng, S., Xie, X. (eds) Social Media Processing. SMP 2017. Communications in Computer and Information Science, vol 774. Springer, Singapore. https://doi.org/10.1007/978-981-10-6805-8_26
Download citation
DOI: https://doi.org/10.1007/978-981-10-6805-8_26
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-10-6804-1
Online ISBN: 978-981-10-6805-8
eBook Packages: Computer ScienceComputer Science (R0)