Using Advanced Analytical Models to Assess Self-Esteem and its Important Predictors in Undergraduate Students
DOI:
https://doi.org/10.71317/kjard.2.11.2026.1024Keywords:
Self-esteem, Undergraduate, Malakand Division, Machine Learning, Predictors, Psychological Well-beingAbstract
Self-esteem is an important psychological concept that plays a major role in determining academic achievement, emotional state and social adaptation among college students. This paper examine the occurrence of self-esteem and the factors which impact self-esteem with key factors identified in undergraduate students in universities at the Malakand Division, Pakistan using machine learning models. A cross-sectional survey was done and a representative sample of students was gathered with the help of which demographic, academic, social, and psychological data were obtained. The data were analyzed using machine learning models, Random Forest, Support Vector Machine (SVM), Gradient Boosting Machine (GBM), and Logistic Regression. Confusion matrix were used to assess the performance of these four machine learning models. The study show that 55.70% students have normal self-esteem and 44.30% student have low self-esteem. The results show that there is a significant difference in the level of self-esteem amongst students and is largely influenced by various factors, including income, GPA and weight of the students. Machine learning models were found to be quite efficient at detecting complex and nonlinear associations amid predictors and showed much higher accuracy levels than conventional statistics. The outcomes can be used to underscore the usefulness of data-driven methods in the study of psychological constructs and emphasize the importance of specific interventions as the means of boosting the self-esteem of the students. The work is informative to the university administrators, policymakers and mental health professionals, and offers an evidence-based model of what counseling programs, peer support programs and academic mentoring strategies can be designed to achieve the goals of promoting student well-being in culturally and socioeconomically divergent settings.
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Zahid Khan, Sulaiman Khan, Jawad Ahmad, Haroon Ur Rahid, Niaz Muhammad (Author)

This work is licensed under a Creative Commons Attribution 4.0 International License.










