Clustering and Classification Models For Student's Grit Detection in E-Learning

Abstract

Grit plays a crucial role in determining high individual success more than intellectual talent alone. However, there is no existing literature that ventured into the trait identification in an e-learning environment. This study presents a comprehensive computational-driven strategy for detecting a learner's grit using machine learning. Empirical results show that DBSCAN and Random Forest models produce average accurate prediction consistency of 92.67% against the questionnaire method. Knowledge interpretation using feature importance and association mining quantifies perseverance and sustained interest as the most pressing component of grit. Correlational analysis reveals that grit has a weak connection with course grades (short-term goal) but demonstrates a strong positive association with professional achievement (long-term goal) and maturation. Collectively, our findings substantiate that breakthrough accomplishment is contingent not solely on cognitive ability but on constant interests and resilience.