ARTIFICIAL INTELLIGENCE APPLICATIONS IN SOCIAL PEDAGOGY: PREDICTIVE ANALYTICS FOR EARLY INTERVENTION ENHANCEMENT
DOI:
https://doi.org/10.46991/educ-21st-century.v7.i2.259Keywords:
Artificial Intelligence (AI) , Predictive Analytics, School Dropout Risk, Early Intervention, Social Pedagogy, Machine Learning Models, Bias and Fairness in AI, Data Privacy, Decision Curve Analysis (DCA), Educational Data MiningAbstract
Early identification of children and families in need of support is a critical task in social pedagogy. This paper examines how Artificial Intelligence (AI) systems can augment the social pedagogue’s work by predicting risk factors and detecting the need for early interventions. We present a study using a predictive analytics approach to flag at-risk students, applying a regression model to educational and socio-demographic data. The model’s results indicate that AI-driven analytics can successfully identify a significant portion of at-risk youths, allowing interventions before issues escalate. We discuss these findings in the context of existing literature, highlighting the benefits of AI—improved accuracy, efficiency, and resource allocation—alongside the challenges, such as ethical considerations and the need for human oversight. The study concludes that AI systems, when used responsibly, have the potential to greatly enhance early intervention strategies in social pedagogy, supporting social pedagogues in making informed, timely decisions to improve outcomes for vulnerable populations.
References
1. Arishi H., Falkner N., Treude C., & Attapattu T., Systematic Literature Review on Machine Learning Research in Education. In 2021 IEEE Frontiers in Education Conference (FIE), October, 2024, pp. 1–9. doi: 10.1109/fie61694.2024.10892898
2. Bañeres D., Rodríguez-González M.E., Guerrero-Roldán A.E., & Cortadas P., An early warning system to identify and intervene online dropout learners. International Journal of Educational Technology in Higher Education, 20(1), January, 2023. doi: 10.1186/s41239-022-00371-5
3. Inkster B., et al.. User engagement with mental health chatbots: A study on digital therapy adherence. In Proceedings of the European Conference on Digital Psychiatry, Berlin, Germany, 2018, pp. 67–75.
4. Lupariello F., Sussetto L., Di Trani S., & Di Vella G., Artificial Intelligence and Child Abuse and Neglect: A Systematic Review. Children, 10(10), October, 2023, 1659. doi: 10.3390/children10101659
5. Nuwasiima N.M., Ahonon N.M.P., & Kadiri N.C., The Role of Artificial Intelligence (AI) and Machine Learning in Social Work Practice. World Journal of Advanced Research and Reviews, 24(1), October, 2024, 80–97. doi: 10.30574/wjarr.2024.24.1.2998
6. Psyridou M., Prezja F., Torppa M., Lerkkanen M.K., Poikkeus A.M., & Vasalampi K., Machine learning predicts upper secondary education dropout as early as the end of primary school. Scientific Reports, 14(1), June, 2024. doi: 10.1038/s41598-024-63629-0
7. Schwartz D.R., Kaufman A.B., & Schwartz I.M., Computational intelligence techniques for risk assessment and decision support. Children and Youth Services Review, 26(11), September, 2004, 1081–1095. doi: 10.1016/j.childyouth.2004.08.007
8. San Diego State University, Academy for Professional Excellence, Use of AI Tools in Social Work and Child Welfare Services (Research Summary). San Diego, CA, USA. Available: CWDS Research Summary: Use of AI Tools in Social Work and Child Welfare Services — October 2023, October, 2023.
Downloads
Published
Issue
Section
License
Copyright (c) 2025 Samvel Asatryan
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
