Development of Machine Learning Models for Predicting Academic Stress in Adolescents: A Survey on Mental Health Status of Adolescents in 2021
Abstract
In the field of social science research, traditional statistical methods have been predominantly used to analyze the major causes of adolescent stress. Most existing studies focus on this approach. In relation to academic stress, this study aims to develop an analysis model based on artificial intelligence and machine learning-driven statistical methods, utilizing big data analysis. Academic stress has a significant impact on the mental health of adolescents, and predicting it can provide valuable insights into students' stress levels, ultimately suggesting effective ways to alleviate their stress. The collected data was sourced from the 2021 Korea Children and Youth Data Archive survey, where 225 common variables were selected. To identify specific variables influencing adolescent academic stress and to choose the most effective machine learning method, five regression models—Random Forest, Linear Regression, Ridge, Lasso, and Gradient Boosting—were applied to determine significant variables.
The performance of these regression models was evaluated using Mean Absolute Error (MAE), Root Mean Squared Error (RMSE), and R² Score as assessment metrics. Based on these evaluations, Gradient Boosting was selected as the most effective predictive model. Additionally, an analysis of variable importance was conducted to identify key factors affecting academic stress
References
- Cha Son. Min, “Korean Youth's Life Satisfaction 'Lowest' vs Academic Performance 'Top'”, 2024. https://www.newsis.com/view/NISX20240105_0002582920
- Min ju. Cha, “Korean Students Stuck In 'Study Hell', 41% Are 'Stressed'”, 2023. https://www.kmib.co.kr/article/view.asp?arcid=0924304673
- Hee jin. Han, "Factors affecting academic stress perceived by high school students. Personality education," Vol.16, No.3, pp.103-117, 2022.
- JH Kim, SB Kim, JI Jeong, "The Effects of Adolescents' Academic Stress on School Life Adaptation: Focusing on the Mediating Effects of Stress Coping," The Korean Youth Study, Vol.25, No.4, pp.241-269, 2014.
- SC Shin, SY Chol, "Academic stress perceived by adolescents to adapt to school life." The moderating effect of self-esteem on the effect", counseling psychological education welfare, Vol.6, No.3, pp.59-72, 2019.
- JI Jang, SB Kim, "The mediating effect of positive psychological capital and smartphone addiction in the relationship between adolescents' stress and school life adaptation." Youth Counseling Study, Vol.23, No.2, pp.447-465, 2015.
- DW Kim, HY Park, KI Lee, "The Effects of Parents' Academic Support and Emotional Support on Academic Stress and the Controlling Effect of Intrinsic Motivation," Human Development Research, Vol. 29 No.1, pp.21-41, 2022.
- CR Noh, SH Kim, "The Effects of Academic Stress and Academic Performance of Middle School Students on Psychological Well-being," Korean Department of Child Welfare, 39, 2021.
- KH Lee, "Study on the Stress of Adolescents", Ph.D. thesis, Sookmyung Women's University, 1995.
- GY Kim, "School life and counseling guidance", 560 Hakjisa, 2000.
- EH Choi, "The effect of academic stress in high school students on school life adaptation. Mediating effects of psychological state and moderating effects of parenting attitudes," 120, master's thesis, Daegu Oriental Medical University, 2016.
- HK Sang, YN Lee, "The relationship between academic achievement and academic stress: the moderating effect of academic self-concept," Educational Research, Vol.35, No.1, pp.53-71, 2012.
- MH Oh, SM Chun, "The Effects of Meditation Training to Analysis of Academic Stress Factors and Symptoms in Middle School Students and their Reduction", 78, master's thesis, Kyungpook National University, 1994.
- SM Mo, "Analyzing the moderating effects of adolescent academic stress-inducing variables: Focusing on self-esteem and decision-making autonomy", Journal of the Future Youth Society, Vol.7, No.2, pp.49-66, 2010.
- SM Kwon, "Study on the Predictive Model of Credit Ratings for Logistics Companies Using Machine Learning", 173, PhD thesis, Chung-Ang University, 2023.
- HS Seo, “Statistical Machine Learning for the Selection of Linear Models: A Comparative Study of Variable Selection Methods”, Journal of The Korean Data Analysis Society, Vol.23, No.6, pp.2643-2653, 2021.
- John Kelleher, Brendan Tierney, OS Kwon, “Data Science as a Tool for Insight for Better Decision Making,” 272, Kim Young-sa, 2019.
- A Muller, S Guido, "Introduction to Machine Learning with Python," 504, Hanbit Media, 2017.
- JW Lee, "Machine Learning-Based Big Data Analysis for Frost Occurrence Prediction Modeling," 113, Hanbat National University, 2022.
- SY Kim, YJ Jeong, TH Kim, "First Steps in Machine Learning: From Basics to Modeling, Practical Examples, and Problem Solving," 376, Hanbit Media, 2017.
Keywords
Details
| Section | Articles |
| Issue | Vol. 1 No. 2 (2025): Volume 1 Issue 2 (May 2025) |
| Published | 2025-05-30 |
| Pages | 2-19 |
- Graduated from Seoul School of Integrated Sciencs & Technologies(aSSIST),
- Graduate School of AI, Department of AI Advanced Studies, Major in AI
- Big Data(Master of Engineering)
- Research Interests : AI, Digital Transformation, Generative AI, Data Analysis etc.
- Assistant Professor at Seoul School of Intergrated Sciences & Technologies(aSSIST)
- Assistant Professor, University of Mississippi(2018-2022)
- Ph.D. in Sports Management, Seoul National University
- Research Interests : AI, Sports Analytics, Sports Marketing, Sports Media, Big Data Analytics etc.
License
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.