Date
Publisher
arXiv
The study explores the potential of AI technologies in personalized learning,
suggesting the prediction of academic success through leadership personality
traits and machine learning modelling. The primary data were obtained from 129
master's students in the Environmental Engineering Department, who underwent
five leadership personality tests with 23 characteristics. Students used
self-assessment tools that included Personality Insight, Workplace Culture,
Motivation at Work, Management Skills, and Emotion Control tests. The test
results were combined with the average grade obtained from academic reports.
The study employed exploratory data analysis and correlation analysis. Feature
selection utilized Pearson correlation coefficients of personality traits. The
average grades were separated into three categories: fail, pass, and excellent.
The modelling process was performed by tuning seven ML algorithms, such as SVM,
LR, KNN, DT, GB, RF, XGBoost and LightGBM. The highest predictive performance
was achieved with the RF classifier, which yielded an accuracy of 87.50% for
the model incorporating 17 personality trait features and the leadership mark
feature, and an accuracy of 85.71% for the model excluding this feature. In
this way, the study offers an additional opportunity to identify students'
strengths and weaknesses at an early stage of their education process and
select the most suitable strategies for personalized learning.
Study at a glance
- Question: Can machine learning models predict students' academic grade categories using their leadership personality traits?
- Setting and data: 129 master's students from 17 countries in an Environmental Engineering Department, evaluated using five self-assessment tests and academic grades.
- Method: Machine learning classification comparing seven algorithms with hyperparameter tuning and five-fold cross-validation.
Why it matters
Personalized learning relies on understanding character traits that impact performance. While general personality traits have been studied, little research examines how specific leadership personality traits relate to students' academic grades using predictive machine learning models.
Key findings
- A Random Forest model predicted student grade categories with 87.50% accuracy when including a leadership mark, and 85.71% accuracy using only 17 personality traits.
- Emotional stability was the most valuable predictive feature across models, followed by achievement, achievement culture, and purpose.
- Status motivation positively correlated with average grades, whereas achievement, extraversion, entrepreneurial culture, failure aversion, emotional stability, and agreeableness showed negative correlations.
Summary drafted with AI from the full paper and may contain errors. See the full paper for details.
What is the application?
Who age?
Study design
