RT journal article
T1 Developing a Model to Predict Self-Reported Student Performance during Online Education Based on the Acoustic Environment
A1 Puyana Romero, Virginia
A1 Larrea Álvarez, César Marcelo
A1 Díaz Márquez, Angela María
A1 Hernández Molina, Ricardo
A1 Ciaburro, Giuseppe
A2 Máquinas y Motores Térmicos
K1 online learning
K1 domestic soundscape
K1 self-reported academic performance
K1 noise sources
K1 machine learning
AB In recent years, great developments in online university education have been observed,favored by advances in ICT. There are numerous studies on the perception of academic performancein online classes, influenced by aspects of a very diverse nature; however, the acoustic environmentof students at home, which can certainly affect the performance of academic activities, has barelybeen evaluated. This study assesses the influence of the home acoustic environment on students’self-reported academic performance. This assessment is performed by calculating prediction modelsusing the Recursive Feature Elimination method with 40 initial features and the following classifiers:Random Forest, Gradient Boosting, and Support Vector Machine. The optimal number of predictorsand their relative importance were also evaluated. The performance of the models was assessedby metrics such as the accuracy and the area under the receiver operating characteristic curve(ROC_AUC-score). The model with the smallest optimal number of features (with 14 predictors, 9of them about the perceived acoustic environment) and the best performance achieves an accuracyof 0.7794; furthermore, the maximum difference for the same algorithm between using 33 and14 predictors is 0.03. Consequently, for simplicity and the ease of interpretation, models with areduced number of variables are preferred.
PB MDPI
SN 2071-1050
YR 2024
FD 2024-05-23
LK http://hdl.handle.net/10498/33002
UL http://hdl.handle.net/10498/33002
LA eng
DS Repositorio Institucional de la Universidad de Cádiz
RD 22-sep-2026