| Abstract | Emotional intelligence (EI) has emerged as a crucial factor influencing academic success among college
students. This study explores the impact of key EI components—self-awareness, self-regulation, motivation,
empathy, and social skills—on academic achievement by utilizing XGBoost, a state-of-the-art machine
learning algorithm renowned for its predictive accuracy.
The primary aim is to assess the relative importance of various EI traits in predicting students’ academic
performance and to construct a robust predictive model that highlights the most influential emotional
intelligence factors contributing to student success. The analysis is conducted on a dataset comprising EI
assessment scores and academic records of college students. XGBoost is applied for both feature importance
analysis and predictive modeling.
The results identify which EI dimensions have the most significant impact on academic outcomes,
offering valuable insights for educators, counselors, and policymakers aiming to design targeted
interventions and support strategies. By leveraging advanced machine learning techniques, this research
provides a data-driven perspective on the role of emotional intelligence in education, contributing
meaningfully to existing literature and enhancing approaches to student performance improvement.
Keywords: Emotional Intelligence, Academic Achievement, XGBoost, Machine Learning, Predictive
Modeling, Student Performance
|
|---|
