2025
Marticorena-Sánchez, Raúl; Canepa-Oneto, Antonio; López-Nozal, Carlos; Barbero-Aparicio, José A.
Unveiling the Differences in Early Performance Prediction Between Online Social Sciences and STEM Courses Using Educational Data Mining Journal Article
In: Expert Systems, vol. 42, no. 3, pp. e13837, 2025.
Abstract | Links | BibTeX | Tags: Educational data mining, Learning analytics, Learning at scale, Online learning logs, Student performance prediction, Supervised data-mining
@article{marticorena2025,
title = {Unveiling the Differences in Early Performance Prediction Between Online Social Sciences and STEM Courses Using Educational Data Mining},
author = {Raúl Marticorena-Sánchez and Antonio Canepa-Oneto and Carlos López-Nozal and José A. Barbero-Aparicio},
editor = {Wiley},
url = {https://doi.org/10.1111/exsy.13837
https://onlinelibrary.wiley.com/doi/abs/10.1111/exsy.13837},
doi = {10.1111/exsy.13837},
year = {2025},
date = {2025-01-20},
journal = {Expert Systems},
volume = {42},
number = {3},
pages = {e13837},
abstract = {Educational Data Mining and Learning Analytics in virtual environments can be used to diagnose student performance problems at an early stage. Information that is useful for guiding the decisions of teachers managing academic training, so that students can successfully complete their course. However, student interaction patterns may vary depending on the knowledge domain. Our aim is to design a framework applicable to online Social Sciences and STEM courses, recommending methods for building accurate early performance prediction models. A large-scale comparative study of the accuracy of multiple classifiers applied to classify the interaction logs of 32,593 students from 9 Social Sciences and 13 STEM courses is presented. Corroborating the results of other works, it was observed that high early performance prediction accuracy was obtained based on nothing other than student logs: accuracies of 0.75 in the 10th week, 0.80 in the 20th week, 0.85 in the 30th week and 0.90 in the 40th week. However, accuracy rates were observed to vary significantly, in relation to the classification algorithm and the knowledge domain (Social Sciences vs. STEM). These predictions are generally less accurate for Social Sciences compared to STEM courses, especially at the beginning of the course, with fewer differences observed in the final weeks. Additionally, this research identifies instances of low-accuracy outliers in the prediction of Social Sciences courses over time. These findings highlight the complex challenges and variations in early performance prediction across different domains in online education.},
keywords = {Educational data mining, Learning analytics, Learning at scale, Online learning logs, Student performance prediction, Supervised data-mining},
pubstate = {published},
tppubtype = {article}
}
Educational Data Mining and Learning Analytics in virtual environments can be used to diagnose student performance problems at an early stage. Information that is useful for guiding the decisions of teachers managing academic training, so that students can successfully complete their course. However, student interaction patterns may vary depending on the knowledge domain. Our aim is to design a framework applicable to online Social Sciences and STEM courses, recommending methods for building accurate early performance prediction models. A large-scale comparative study of the accuracy of multiple classifiers applied to classify the interaction logs of 32,593 students from 9 Social Sciences and 13 STEM courses is presented. Corroborating the results of other works, it was observed that high early performance prediction accuracy was obtained based on nothing other than student logs: accuracies of 0.75 in the 10th week, 0.80 in the 20th week, 0.85 in the 30th week and 0.90 in the 40th week. However, accuracy rates were observed to vary significantly, in relation to the classification algorithm and the knowledge domain (Social Sciences vs. STEM). These predictions are generally less accurate for Social Sciences compared to STEM courses, especially at the beginning of the course, with fewer differences observed in the final weeks. Additionally, this research identifies instances of low-accuracy outliers in the prediction of Social Sciences courses over time. These findings highlight the complex challenges and variations in early performance prediction across different domains in online education.