Yih-Chang Chen

Predictive Risk Identification and Resource Optimization in Social Work: A Hybrid Semi-Supervised Learning Framework

PDF (730KB), PP.66-82

Views: 0 Downloads: 0

Author(s)

Yih-Chang Chen ^1,*

1. Department of Social Work, Chang Jung Christian University, Tainan, Taiwan, China

* Corresponding author.

DOI: https://doi.org/10.5815/ijitcs.2026.05.05

Received: 11 Mar. 2026 / Revised: 19 May 2026 / Accepted: 14 Jul. 2026 / Published: 8 Oct. 2026

Index Terms

Semi-Supervised Learning, Resource Allocation Optimization, Social Work Analytics, High-Risk Family Identification, Early Warning Systems

Abstract

Social work practice faces critical challenges in accurately identifying high-risk families for timely intervention due to limited labeled data. This research develops an intelligent system integrating supervised and semi-supervised learning for early warning, coupled with uncertainty-aware resource optimization. We propose a hybrid framework combining Self-training and Co-training leveraging 1,200 labeled and 13,800 unlabeled family cases. The proposed method achieves 85.6% accuracy and 82.4% recall on the high-risk class, with 95% confidence intervals, substantially outperforming supervised-only baselines. A multi-objective allocation model balances effectiveness, cost, and equity while incorporating prediction uncertainty via robust optimization. Sensitivity analysis over 500 bootstrap scenarios demonstrates service quality guarantees. Subgroup fairness audits show consistent recall across demographic groups (max gap 1.2%). The optimized allocation reduces manpower by 22% while improving intervention success from 68.5% to 84.2%. SHAP-based explainability and human oversight support ethical deployment in social services.

Cite This Paper

Yih-Chang Chen, "Predictive Risk Identification and Resource Optimization in Social Work: A Hybrid Semi-Supervised Learning Framework", International Journal of Information Technology and Computer Science(IJITCS), Vol.18, No.5, pp.66-82, 2026. DOI:10.5815/ijitcs.2026.05.05

Reference

[1]M. A. Alemayehu, S. D. Kebede, A. D. Walle, D. N. Mamo, E. B. Enyew, and J. B. Adem, “A stacked ensemble machine learning model for the prediction of pentavalent 3 vaccination dropout in East Africa,” Frontiers in Big Data, vol. 8, p. 1522578, 2025. doi: 10.3389/fdata.2025.1522578
[2]T. Kyriazos and M. Poga, “Application of machine learning models in social sciences: Managing nonlinear relationships,” Encyclopedia, vol. 4, no. 4, pp. 1790–1805, 2024. doi: 10.3390/encyclopedia4040118
[3]D. Roesler, S. Johnny, M. Conway, et al., “A theory-informed deep learning approach to extracting and characterizing substance use-related stigma in social media,” BMC Digital Health, vol. 2, p. 60, 2024. doi: 10.1186/s44247-024-00065-0
[4]S. Sarker, M. K. Paul, S. T. H. Thasin, and M. A. M. Hasan, “Analyzing students’ academic performance using educational data mining,” Computers and Education: Artificial Intelligence, vol. 7, p. 100263, 2024. doi: 10.1016/j.caeai.2024.100263
[5]C. Jian, J. Gao, and Y. Ao, “A new sampling method for classifying imbalanced data based on support vector machine ensemble,” Neurocomputing, vol. 193, pp. 115–122, 2016. doi: 10.1016/j.neucom.2016.02.006
[6]M. Quimiz-Moreira, R. Delgadillo, J. Parraga-Alava, N. Maculan, and D. Mauricio, “Factors, prediction, explainability, and simulating university dropout through machine learning: A systematic review, 2012–2024,” Computation, vol. 13, no. 8, p. 198, 2025. doi: 10.3390/computation13080198
[7]S. F. Hall, M. Sage, C. F. Scott, and K. Joseph, “A systematic review of sophisticated predictive and prescriptive analytics in child welfare: Accuracy, equity, and bias,” Child and Adolescent Social Work Journal, Advance online publication, 2023. doi: 10.1007/s10560-023-00931-2
[8]M. Rosholm, S. T. Bodilsen, B. Michel, and A. S. Nielsen, “Predictive risk modeling for child maltreatment detection and enhanced decision-making: Evidence from Danish administrative data,” PLoS One, vol. 19, no. 7, e0305974, July 2024. doi: 10.1371/journal.pone.0305974
[9]R. Vaithianathan, D. Benavides-Prado, R. Rebbe, and E. Putnam-Hornstein, “Using a predictive risk model to prioritize families for prevention services: The Hello Baby Program in Allegheny County, PA,” Prevention Science, vol. 26, no. 3, pp. 321–330, 2025. doi: 10.1007/s11121-025-01802-1
[10]T. Jiang, J. Gradus, and A. Rosellini, “Supervised machine learning: A brief primer,” Behavior Therapy, vol. 51, no. 5, pp. 645–658, 2020. doi: 10.1016/j.beth.2020.05.002
[11]P. Kostakos, L. Špráchalová, A. Pandya, M. Aboeleinen, and M. Oussalah, “Covert online ethnography and machine learning for detecting individuals at risk of being drawn into online sex work,” in 2018 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining (ASONAM), 2018, pp. 1096–1099. doi: 10.1109/ASONAM.2018.8508276
[12]P. Cruz-Gonzalez, A. W. He, E. P. Lam, I. M. C. Ng, M. W. Li, R. Hou, J. N. Chan, Y. Sahni, N. Vinas Guasch, T. Miller, B. W. Lau, and D. I. Sánchez Vidaña, “Artificial intelligence in mental health care: A systematic review of diagnosis, monitoring, and intervention applications,” Psychological Medicine, vol. 55, e18, 2025. doi: 10.1017/S0033291724003295
[13]M. Lovitt, H. Ma, S. Wang, and Y. Peng, “Suicide risk assessment on social media with semi-supervised learning,” in 2024 IEEE International Conference on Big Data (BigData), IEEE, 2024, pp. 8541–8549. doi: 10.1109/BigData62323.2024.10825422
[14]C. Mimikou, C. Kokkotis, D. Tsiptsios, K. Tsamakis, S. Savvidou, L. Modig, F. Christidi, A. Kaltsatou, T. Doskas, C. Mueller, A. Serdari, K. Anagnostopoulos, and G. Tripsianis, “Explainable machine learning in the prediction of depression,” Diagnostics (Basel), vol. 15, no. 11, pp. 1412, 2025. doi: 10.3390/diagnostics15111412
[15]K. M. O. Vale, A. C. Gorgônio, F. D. L. Gorgônio, and A. M. D. P. Canuto, “An efficient approach to select instances in self-training and co-training semi-supervised methods,” IEEE Access, vol. 10, pp. 7254–7276, 2022. doi: 10.1109/ACCESS.2021.3138682
[16]X. Zhao, Y. Wang, J. Li, W. Liu, Y. Yang, Y. Qiao, J. Liao, M. Chen, D. Li, B. Wu, D. Huang, and D. Wu, “A machine-learning-derived online prediction model for depression risk in COPD patients: A retrospective cohort study from CHARLS,” J. Affect. Disord., vol. 377, pp. 284–293, 2025. doi: 10.1016/j.jad.2025.02.063
[17]L. Zheng, O. Wang, S. Hao, C. Ye, M. Liu, M. Xia, A. N. Sabo, L. Markovic, F. Stearns, L. Kanov, K. G. Sylvester, E. Widen, D. B. McElhinney, W. Zhang, J. Liao, and X. B. Ling, “Development of an early-warning system for high-risk patients for suicide attempt using deep learning and electronic health records,” Translational Psychiatry, vol. 10, no. 1, p. 72, 2020. doi: 10.1038/s41398-020-0684-2
[18]A. Blum and T. Mitchell, “Combining labeled and unlabeled data with co-training,” in Proc. 11th Annu. Conf. Comput. Learn. Theory, 1998, pp. 92–100.
[19]Y. Wang, S. Shi, X. Wei, Y. Wu, Y. Shi, and J. Cai, “Application and analysis of random forest and support vector classification in risk prediction of childhood obesity and hyperuricemia,” Diabetes, Metabolism Syndrome and Obesity: Targets and Therapy, vol. 18, pp. 2221–2233, 2025. doi: 10.2147/DMSO.S519284
[20]C. Berkel, D. C. Knox, N. Flemotomos, V. R. Martinez, D. C. Atkins, S. S. Narayanan, L. A. Rodriguez, C. G. Gallo, and J. D. Smith, “A machine learning approach to improve implementation monitoring of family-based preventive interventions in primary care,” Implementation Research and Practice, vol. 4, 2023. doi: 10.1177/26334895231187906
[21]L. Series and L. Clements, “Putting the cart before the horse: Resource allocation systems and community care,” J. Soc. Welfare Fam. Law, vol. 35, no. 2, pp. 207–226, 2013. doi: 10.1080/09649069.2013.800288
[22]Unceta, B. Salbanya, J. Coll, M. Villaret, and J. Nin, “Optimizing resource allocation in home care services using MaxSAT,” Cognitive Systems Research, vol. 88, 101291, 2024. doi: 10.1016/j.cogsys.2024.101291
[23]A. P. Dawid, "The Well-Calibrated Bayesian," J. Amer. Statist. Assoc., vol. 77, no. 379, pp. 605–610, 1982. doi: 10.1080/01621459.1982.10477856
[24]Z. H. Zhou and M. Li, "Semi-supervised learning by disagreement," Knowl. Inf. Syst., vol. 24, pp. 415–439, 2010. doi: 10.1007/s10115-009-0209-z
[25]M. Hardt, E. Price, and N. Srebro, "Equality of opportunity in supervised learning," in Proc. 30th Int. Conf. Neural Inf. Process. Syst. (NIPS'16), Red Hook, NY, USA: Curran Associates Inc., 2016, pp. 3323–3331.
[26]A. Ben-Tal, L. El Ghaoui, and A. Nemirovski, Robust Optimization. Princeton: Princeton University Press, 2009. doi: 10.1515/9781400831050

International Journal of Information Technology and Computer Science (IJITCS)