v1 Exploring internet addiction among Adolescents in China: A comparison between the only-children and non-only children using optimized tree-based machine learning models
Keywords:
Internet addiction, only-child, non-only child, machine learning, adolescents, ChinaAbstract
Introduction: One-child policy in China has led to the emergence of a demographic of only-children, who encounter unique psychological, and familial dynamics. We explored the key predictors for internet addiction (IA) and compared the differences between adolescents from only-child and non-only-child families.
Method: From April to May 2023, 8176 adolescents were randomly selected from six junior high schools in Henan Province. Internet addiction (IA) was assessed using the Internet Addiction Test (IAT). Random Forest (RF) model identified key features using recursive feature elimination (RFE), Boruta, variance threshold, and SelectKBest. Tree-based machine learning models were developed with five-fold cross-validation and hyperparameter optimization (GridSearchCV, RandomizedSearchCV, BayesSearchCV). Model performance was evaluated using accuracy, precision, recall, F1-score, and ROC-AUC.
Results: Only-children comprised 8.64% (n=706) of the study participants. The prevalence of IA was slightly higher among only-child adolescents (20.54%) compared to their non-only-child counterparts (19.26%). Negative life events, psychological resilience, classmate support, school belonging, parent-child cohesion, and self-esteem were shared predictors, while low teacher support and poor sleep quality uniquely predicted IA in only-children and non-only-children, respectively. RF model with BayesSearchCV performed best for only-children (80% accuracy, 76% F1-score), while XGBoost excelled for non-only-children (83% accuracy, 79% F1-score).
Conclusion: The study highlights subtle differences in IA prevalence and predictors between only-child and non-only-child adolescents. While shared predictors underscore common vulnerabilities, unique factors like teacher support sleep quality emphasize tailored intervention needs. Machine learning models effectively predicted IA, with RF excelling for only-children and XGBoost for non-only-children, offering robust tools for targeted prevention strategies.
References
Alimoradi, Z., Lin, C.-Y., Broström, A., Bülow, P. H., Bajalan, Z., Griffiths, M. D., Ohayon, M. M., & Pakpour, A. H. (2019). Internet addiction and sleep problems: A systematic review and meta-analysis. Sleep medicine reviews, 47, 51-61.
Arnold, C., Biedebach, L., Küpfer, A., & Neunhoeffer, M. (2024). The role of hyperparameters in machine learning models and how to tune them. Political Science Research and Methods, 12(4), 841-848.
Arslan, G., & Duru, E. (2017). Initial development and validation of the School Belongingness Scale. Child Indicators Research, 10, 1043-1058.
Bergstra, J., & Bengio, Y. (2012). Random search for hyper-parameter optimization. Journal of machine learning research, 13(2).
Bischl, B., Binder, M., Lang, M., Pielok, T., Richter, J., Coors, S., Thomas, J., Ullmann, T., Becker, M., & Boulesteix, A. L. (2023). Hyperparameter optimization: Foundations, algorithms, best practices, and open challenges. Wiley Interdisciplinary Reviews: Data Mining and Knowledge Discovery, 13(2), e1484.
Brockmeier, L. C., Keller, J., Dingler, T., Paduszynska, N., Luszczynska, A., & Radtke, T. (2025). Planning a Digital Detox: Findings from a Randomized Controlled Trial to Reduce Smartphone Usage Time. Computers in human behavior, 108624.
Buri, J. (2018). Negative life events scale for students (NLESS). College Student Journal, 52(3), 361-367.
Cai, J., Wang, Y., Wang, F., Lu, J., Li, L., & Zhou, X. (2021). The association of parent-child communication with internet addiction in left-behind children in china: a cross-sectional study. International Journal of Public Health, 66, 630700.
Cameron, L., Erkal, N., Gangadharan, L., & Meng, X. (2013). Little emperors: behavioral impacts of China's One-Child Policy. Science, 339(6122), 953-957.
Cao, Q., An, J., Yang, Y., Peng, P., Xu, S., Xu, X., & Xiang, H. (2022). Correlation among psychological resilience, loneliness, and internet addiction among left-behind children in China: A cross-sectional study. Current Psychology, 41(7), 4566-4573.
Carpenter, J. S., & Andrykowski, M. A. (1998). Psychometric evaluation of the Pittsburgh sleep quality index. Journal of psychosomatic research, 45(1), 5-13.
Çelebioğlu, A., Aytekin Özdemir, A., Küçükoğlu, S., & Ayran, G. (2020). The effect of Internet addiction on sleep quality in adolescents. Journal of Child and Adolescent Psychiatric Nursing, 33(4), 221-228.
Chen, H., Covert, I. C., Lundberg, S. M., & Lee, S.-I. (2023). Algorithms to estimate Shapley value feature attributions. Nature machine intelligence, 5(6), 590-601.
Chen, T. (2015). Xgboost: extreme gradient boosting. R package version 0.4-2, 1(4).
Chen, W., Li, X., Huebner, E. S., & Tian, L. (2022). Parent–child cohesion, loneliness, and prosocial behavior: Longitudinal relations in children. Journal of Social and Personal Relationships, 39(9), 2939-2963.
Chen, Y., Swee, E. L., & Wang, H. (2023). Little emperors in the workplace: Labor market consequences of China's one-child policy. China Economic Review, 80, 101985.
Cheng, T. O. (2013). China's little emperors: medical consequences of China's one-child policy. In (Vol. 168, pp. 5121-5125): Elsevier.
Chi, X., Hong, X., & Chen, X. (2020). Profiles and sociodemographic correlates of Internet addiction in early adolescents in southern China. Addictive behaviors, 106, 106385.
Chi, X., Huang, L., Wang, J., & Zhang, P. (2020). The prevalence and socio-demographic correlates of depressive symptoms in early adolescents in China: Differences in only child and non-only child groups. International journal of environmental research and public health, 17(2), 438.
CNNI. (2022). The 50th China statistical report on Internet development. Retrieved December 10, 2024, from https://www.cnnic.net.cn/n4/2022/0401/c88-1131.html
Connor, K. M., & Davidson, J. R. (2003). Development of a new resilience scale: The Connor‐Davidson resilience scale (CD‐RISC). Depression and anxiety, 18(2), 76-82.
Deng, A.-P., Wang, C., Cai, J., Deng, Z.-Y., Mu, Y.-F., Song, H.-J., Meng, Y.-J., Meng, X.-D., Huang, X.-H., & Zhang, L. (2023). Effects of internet addiction and academic satisfaction on mental health among college students after the lifting of COVID-19 restrictions in China. Frontiers in Psychiatry, 14, 1243619.
Falbo, T., & Hooper, S. Y. (2015). China’s only children and psychopathology: A quantitative synthesis. American Journal of Orthopsychiatry, 85(3), 259.
Goodenow, C. (1993). The psychological sense of school membership among adolescents: Scale development and educational correlates. Psychology in the Schools, 30(1), 79-90.
Hua, Y., Huang, C., Guo, Y., Du, X., Guo, L., Wang, W., Lu, C., & Guo, L. (2023). Association between academic pressure, NR3C1 gene methylation, and anxiety symptoms among Chinese adolescents: a nested case-control study. BMC psychiatry, 23(1), 376.
Jiang, M.-m., Gao, K., Wu, Z.-y., & Guo, P.-p. (2022). The influence of academic pressure on adolescents’ problem behavior: chain mediating effects of self-control, parent–child conflict, and subjective well-being. Frontiers in psychology, 13, 954330.
Ke, G., Meng, Q., Finley, T., Wang, T., Chen, W., Ma, W., Ye, Q., & Liu, T.-Y. (2017). Lightgbm: A highly efficient gradient boosting decision tree. Advances in neural information processing systems, 30.
Li, D., Li, X., Wang, Y., Zhao, L., Bao, Z., & Wen, F. (2013). School connectedness and problematic Internet use in adolescents: A moderated mediation model of deviant peer affiliation and self-control. Journal of abnormal child psychology, 41, 1231-1242.
Li, J., Huo, M., Gao, L., & Wang, D. (2024). Stigma of Losing an Only Child: Implications for Public Perceptions of Bereavement Adversities and Prosocial Tendencies in China. OMEGA-Journal of Death and Dying, 00302228241303254.
Li, Y., Li, Y., Chen, G., & Yang, J. (2024). Being an only child and children’s prosocial behaviors: evidence from rural China and the role of parenting styles. Humanities and Social Sciences Communications, 11(1), 1-14.
Lundberg, S. M., Erion, G., Chen, H., DeGrave, A., Prutkin, J. M., Nair, B., Katz, R., Himmelfarb, J., Bansal, N., & Lee, S.-I. (2020). From local explanations to global understanding with explainable AI for trees. Nature machine intelligence, 2(1), 56-67.
Mo, P. K., Chan, V. W., Wang, X., & Lau, J. T. (2020). Gender difference in the association between internet addiction, self-esteem and academic aspirations among adolescents: A structural equation modelling. Computers & Education, 155, 103921.
Mollayeva, T., Thurairajah, P., Burton, K., Mollayeva, S., Shapiro, C. M., & Colantonio, A. (2016). The Pittsburgh sleep quality index as a screening tool for sleep dysfunction in clinical and non-clinical samples: A systematic review and meta-analysis. Sleep medicine reviews, 25, 52-73.
Ouyang, Y. (2013). China relaxes its one-child policy. The Lancet, 382(9907), e28.
Parmar, A., Katariya, R., & Patel, V. (2019). A review on random forest: An ensemble classifier. International conference on intelligent data communication technologies and internet of things (ICICI) 2018,
Sarıalioğlu, A., Atay, T., & Arıkan, D. (2022). Determining the relationship between loneliness and internet addiction among adolescents during the covid-19 pandemic in Turkey. Journal of pediatric nursing, 63, 117-124.
Sechi, C., Loi, G., & Cabras, C. (2021). Addictive internet behaviors: The role of trait emotional intelligence, self‐esteem, age, and gender. Scandinavian journal of psychology, 62(3), 409-417.
Shangguan, M., Ao, C., & Zhao, J. (2023). Parent-child cohesion and college students’ positive/negative affect: The moderating roles of sympathetic nervous system activity and parent-child separation experience. Journal of Youth and Adolescence, 52(6), 1301-1312.
Wang, J., Hao, Q.-h., Tu, Y., Wang, Y., Peng, W., Li, H., & Zhu, T.-m. (2022). The relationship between negative life events and internet addiction disorder among adolescents and college students in China: a systematic review and meta-analysis. Frontiers in Psychiatry, 13, 799128.
Wang, N., & Hu, Q. (2021). “It is not simply the loss of a child”: The challenges facing parents who have lost their only child in post-reproductive age in China. Death Studies, 45(3), 209-218.
Wang, Q., Wang, H., & Liu, X. (2020). Loneliness, non-suicidal self-injury, and friendship quality among Chinese left-behind adolescents: the role of parent-child cohesion. Journal of affective disorders, 271, 193-200.
Wu, J., Chen, X.-Y., Zhang, H., Xiong, L.-D., Lei, H., & Deng, S.-H. (2019). Hyperparameter optimization for machine learning models based on Bayesian optimization. Journal of Electronic Science and Technology, 17(1), 26-40.
Xu, D.-D., Lok, K.-I., Liu, H.-Z., Cao, X.-L., An, F.-R., Hall, B. J., Ungvari, G. S., Lei, S.-M., & Xiang, Y.-T. (2020). Internet addiction among adolescents in Macau and mainland China: prevalence, demographics and quality of life. Scientific reports, 10(1), 16222.
Ye, X.-L., Zhang, W., & Zhao, F.-F. (2023). Depression and internet addiction among adolescents: a meta-analysis. Psychiatry Research, 326, 115311.
Young, K. (2009). Internet addiction: diagnosis and treatment considerations. Journal of Contemporary Psychotherapy, 39, 241-246.
Young, K. S. (1998). Internet addiction: The emergence of a new clinical disorder. Cyberpsychology & behavior, 1(3), 237-244.
