Machine learning-based classification of father involvement among adolescents using psychosocial data

Egi Dio Bagus Sudewo; Annisa Fitri Mulyani; Muhammad Kunta Biddinika; Reni Yunita

Authors

Egi Dio Bagus Sudewo Universitas Royal, Indonesia https://orcid.org/0009-0003-0239-3012
Annisa Fitri Mulyani Universitas Sumatera Utara, indonesia
Muhammad Kunta Biddinika Universitas Ahmad Dahlan, indonesia
Reni Yunita Universitas Royal, Indonesia

Keywords:

Adolescents, Decision tree, Father involvement, Logistic regression, Random forest

Abstract

Father involvement (FI) is a key determinant in adolescents’ cognitive, emotional, social, and academic development. However, variations in the quality of father child interactions necessitate accurate classification approaches. This study proposes a machine learning (ML) framework to classify adolescents’ FI levels using psychosocial data. A validated Likert-scale FI questionnaire was administered to 195 twelfth-grade students. Two labeling schemes were applied: expert-based psychological categories and score-based classification (10-15 = low, 16-20 = high). Three ML algorithms Logistic Regression, Decision Tree, and Random Forest were evaluated using Python. The results indicate that Logistic Regression achieved 100% accuracy across both labeling schemes, while Random Forest and Decision Tree attained accuracy between 92.31% and 97.44%. The perfect accuracy in Logistic Regression highlights a strong linear correlation between the 20-item psychosocial features and the target labels within this specific dataset. This study provides a robust predictive framework that fills the gap in automated father-involvement assessment, offering a more precise tool for psychological evaluation compared to conventional statistical methods.

References

[1] Y. Sulistyawati, “The Effect of Perceived Father Involvement on Emotional Intelligence in Adolescents,” Dev. Clin. Psychol., 2024, doi: 10.15294/dcp.v5i2.17097.

[2] C. S. Walsh, W. Kliewer, and T. N. Sullivan, “Adolescents’ Subjective Well-Being: The Unique Contribution of Fathers,” 2024, doi: 10.1007/s10566-024-09801-z.

[3] A. F. Mulyani, “Perbedaan Self Esteem Ditinjau dari Peran Father Involvement Pada Remaja di SMA Swasta Muhammadiyah 2 Medan,” 2023. [Online]. Available: https://repositori.uma.ac.id/handle/123456789/21678%0Ahttps://repositori.uma.ac.id/bitstream/123456789/21678/2/198600215 - Annisa Fitri Mulyani - Fulltext.pdf

[4] P. A. Pramesti et al., “Classification of Clove Leaf Blister Blight Disease Severity Using Pre-trained Model VGG16, InceptionV3, and ResNet,” J. Ilmu Komput. dan Inf., vol. 17, no. 2, pp. 159–166, 2024, doi: 10.21609/jiki.v17i2.1237.

[5] R. Angger Saputra and Y. Sibaroni, “Multilabel Hate Speech Classification in Indonesian Political Discourse on X using Combined Deep Learning Models with Considering Sentence Length,” J. Ilmu Komput. dan Inf., vol. 18, no. 1, pp. 113–125, 2025, doi: 10.21609/jiki.v18i1.1440.

[6] P. Dehghan, H. Alashwal, and A. A. Moustafa, “Applications of machine learning to behavioral sciences: focus on categorical data,” Discov. Psychol., vol. 2, no. 1, p. 22, Dec. 2022, doi: 10.1007/s44202-022-00027-5.

[7] Kehinde Josephine Olowe, Ngozi Linda Edoh, Stephane Jean Christophe Zouo, and Jeremiah Olamijuwon, “Comprehensive review of logistic regression techniques in predicting health outcomes and trends,” World J. Adv. Pharm. Life Sci., vol. 7, no. 2, pp. 016–026, Nov. 2024, doi: 10.53346/wjapls.2024.7.2.0039.

[8] M. A. Azkiya and Y. N. Ifriza, “Analysis of Coding Stress Impact on Students Programming Skills with Random Forest and C4.5 Algorithms,” J. Ilmu Komput. dan Inf., vol. 18, no. 2, pp. 167–180, 2025, doi: 10.21609/jiki.v18i2.1487.

[9] F. AABOUB, H. CHAMLAL, and T. OUADERHMAN, “Analysis of the prediction performance of decision tree-based algorithms,” in 2023 International Conference on Decision Aid Sciences and Applications (DASA), IEEE, Sep. 2023, pp. 7–11. doi: 10.1109/DASA59624.2023.10286809.

[10] T. Yamamoto et al., “Clinical psychoinformatics,” in Methodological Approaches for Sleep and Vigilance Research, Elsevier, 2022, pp. 255–279. doi: 10.1016/B978-0-323-85235-7.00013-2.

[11] M. J. Burger and N. T. P. Pang, “Well-being in Asia,” Front. Psychol., vol. 16, p. 1661988, Aug. 2025, doi: 10.3389/fpsyg.2025.1661988.

[12] W. A. Rothenberg et al., “Predicting Adolescent Mental Health Outcomes Across Cultures: A Machine Learning Approach,” J. Youth Adolesc., vol. 52, no. 8, pp. 1595–1619, Aug. 2023, doi: 10.1007/s10964-023-01767-w.

[13] A. J. Mena, N. De Oliveira Cardoso, C. E. Xavier, and I. I. De Lima Argimon, “Técnicas de Machine Learning utilizadas en estudios psicológicos con adolescentes: Una revisión sistemática,” Edupsykhé. Rev. Psicol. y Educ., vol. 19, no. 2, pp. 23–38, Nov. 2022, doi: 10.57087/edupsykhe.v19i2.4440.

[14] Aisyah Durrotun Nafisah, Yuli Kurniawati Sugiyo Pranoto, and Siti Nuzulia, “The Impact of Father Involvement in the Early Childhood Problematic Behavior,” JPUD - J. Pendidik. Usia Dini, vol. 17, no. 1, pp. 14–30, Apr. 2023, doi: 10.21009/JPUD.171.02.

[15] A. L. Vázquez, T. Chou, C. M. Navarro Flores, T. S. Barrett, M. T. Villodas, and M. M. Domenech Rodríguez, “High value correlates of caregiver reported counseling service need and utilization for adolescents at-risk for childhood maltreatment and neglect,” PLoS One, vol. 16, no. 10, p. e0258082, Oct. 2021, doi: 10.1371/journal.pone.0258082.

[16] S. Lopez-Larrosa et al., “Using Machine Learning Techniques to Predict Adolescents’ Involvement in Family Conflict,” Soc. Sci. Comput. Rev., vol. 41, no. 5, pp. 1581–1607, Oct. 2023, doi: 10.1177/08944393221084064.

[17] Q. Ma, “Recent applications and perspectives of logistic regression modelling in healthcare,” Theor. Nat. Sci., vol. 36, no. 1, pp. 185–190, Jul. 2024, doi: 10.54254/2753-8818/36/20240614.

[18] K. Tajima, N. Ichijo, Y. Nakahara, and T. Matsushima, “An Algorithmic Framework for Constructing Multiple Decision Trees by Evaluating Their Combination Performance Throughout the Construction Process,” arXiv.Org, vol. abs/2402.0, 2024, doi: 10.48550/arxiv.2402.06452.

[19] A. Moumen, A. Shafqat, T. Alraqad, E. S. Alshawarbeh, H. Saber, and R. Shafqat, “Divorce prediction using machine learning algorithms in Ha’il region, KSA,” Sci. Rep., vol. 14, no. 1, p. 502, Jan. 2024, doi: 10.1038/s41598-023-50839-1.

[20] J. H. Cabot and E. G. Ross, “Evaluating prediction model performance,” Surgery, vol. 174, no. 3, pp. 723–726, Sep. 2023, doi: 10.1016/j.surg.2023.05.023.