The study focuses on predicting university students' learning performance using various data sources from an Intelligent Tutoring System. By applying different experiments with classification algorithms, the research aims to improve predictions through attribute selection and ensembles. The findings suggest that the best results were achieved when using numerical data and employing ensemble methods. The study highlights the importance of attributes like learning strategies, emotions, and interaction zones in predicting student performance. Furthermore, it emphasizes the potential for personalized responses to learners based on their learning process analysis.
To Another Language
from source content
arxiv.org
Głębsze pytania