928
Views
57
Downloads
2
Crossref
N/A
WoS
2
Scopus
N/A
CSCD
Based on the fourth-wave Beijing College Students Panel Survey (BCSPS), this study aims to provide accurate estimation of the percentage of the potential sexual minorities among the Beijing college students by using machine learning methods. Specifically, we employ random forest (RF), an ensemble learning approach for classification and regression, to predict the sexual orientation of those who were not willing to disclose his/her inherent sexual identity. To overcome the imbalance problem arising from far different numerical proportion of sexual minority and majority members, we adopt the repeated random sub-sampling for training set by partitioning those who expressed heterosexual orientation into different number of splits and further combining each split with those who expressed sexual minority orientation. The prediction from 24-split random forest suggests that youths in Beijing with sexual minority orientation amount to 5.71%, almost two times that of the original estimation 3.03%. The results are robust to alternative learning methods and covariate sets. Besides, it is also suggested that random forest outperforms other learning algorithms, including AdaBoost, Naïve Bayes, support vector machine (SVM), and logistic regression, in dealing with missing data, by showing higher accuracy, F1 score, and area under curve (AUC) value.
Based on the fourth-wave Beijing College Students Panel Survey (BCSPS), this study aims to provide accurate estimation of the percentage of the potential sexual minorities among the Beijing college students by using machine learning methods. Specifically, we employ random forest (RF), an ensemble learning approach for classification and regression, to predict the sexual orientation of those who were not willing to disclose his/her inherent sexual identity. To overcome the imbalance problem arising from far different numerical proportion of sexual minority and majority members, we adopt the repeated random sub-sampling for training set by partitioning those who expressed heterosexual orientation into different number of splits and further combining each split with those who expressed sexual minority orientation. The prediction from 24-split random forest suggests that youths in Beijing with sexual minority orientation amount to 5.71%, almost two times that of the original estimation 3.03%. The results are robust to alternative learning methods and covariate sets. Besides, it is also suggested that random forest outperforms other learning algorithms, including AdaBoost, Naïve Bayes, support vector machine (SVM), and logistic regression, in dealing with missing data, by showing higher accuracy, F1 score, and area under curve (AUC) value.
A. Ghaziani, V. Taylor, and A. Stone, Cycles of sameness and difference in LGBT social movements, Annual Review of Sociology, vol. 42, no. 1, pp. 165–183, 2016.
Y. Y. Wang, Z. S. Hu, K. Peng, Y. Xin, Y. Yang, J. Drescher, and R. S. Chen, Discrimination against LGBT populations in China, Lancet Public Health, vol. 4, no. 9, pp. E440–E441, 2019.
J. H. Lee, K. E. Gamarel, K. J. Bryant, N. D. Zaller, and D. Operario, Discrimination, mental health, and substance use disorders among sexual minority populations, Lgbt Health, vol. 3, no. 4, pp. 258–265, 2016.
W. O’Donohue and C. E. Caselles, Homophobia: Conceptual, definitional, and value issues, Journal of Psychopathology and Behavioral Assessment, vol. 15, no. 3, pp. 177–195, 1993.
Y. Hu, Sex ideologies in China: Examining interprovince differences, The Journal of Sex Research, vol. 53, no. 9, pp. 1118–1130, 2016.
R. Tibshirani, Regression shrinkage and selection via the Lasso: A retrospective, Journal of the Royal Statistical Society. Series B:Methodological, vol. 73, no. 3, pp. 273–282, 2011.
N. Japkowicz and S. Stephen, The class imbalance problem: A systematic study, Intelligent Data Analysis, vol. 6, no. 5, pp. 429–449, 2002.
D. S. Palmer, N. M. O'Boyle, R. C. Glen, and J. B. O. Mitchell, Random forest models to predict aqueous solubility, Journal of Chemical Information and Modeling, vol. 47, no. 1, pp. 150–158, 2007.
P. R. Sterzing, W. F. Auslander, and J. T. Goldbach, An exploratory study of bullying involvement for sexual minority youth: Bully-only, victim-only, and bully-victim roles, Society for Social Work and Research, vol. 5, no. 3, pp. 321–337, 2014.
L. Zeeman, N. Sherriff, K. Browne, N. McGlynn, M. Mirandola, L. Gios, R. Davis, J. Sanchez-Lambert, S. Aujean, N. Pinto, et al., A review of lesbian, gay, bisexual, trans and intersex (LGBTI) health and healthcare inequalities, European Journal of Public Health, vol. 29, no. 5, pp. 974–980, 2019.
P. Probst, B. Bischl, and A. L. Boulesteix, Tunability: Importance of hyperparameters of machine learning algorithms, Journal of Machine Learning Research, vol. 20, no. 53, pp. 1–32, 2019.
J. E. Lane, A new cultural cleavage in post-modern society, Brazilian Journal of Political Economy, vol. 27, no. 3, pp. 375–393, 2007.
Y. T. Suen and R. C. H. Chan, A nationwide cross-sectional study of 15,611 lesbian, gay and bisexual people in China: Disclosure of sexual orientation and experiences of negative treatment in health care, International Journal for Equity in Health, vol. 19, p. 46, 2020.
F. Tang and H. Ishwaran, Random forest missing data algorithms, Statistical Analysis and Data Mining, vol. 10, no. 6, pp. 363–377, 2017.
The articles published in this open access journal are distributed under the terms of the Creative Commons Attribution 4.0 International License (http://creativecommons.org/licenses/by/4.0/).