EUVIMEDEUVIMED entdecken
Crossref

Machine Learning-Based Prediction of Academic Resilience, Self-Concept, and Self-Efficacy

Gunjan Kumari

Contemporaneity of English Language and Literature in the Robotized Millennium · 03.07.2026 · 76

DOI: 10.46632/cellrm/5/2/10 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Contemporaneity of English Language and Literature in the Robotized Millennium, online erschienen am 03.07.2026. Verfasst von Gunjan Kumari. Die Arbeit nennt 35 Literaturangaben.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The academic resilience of students is very important in helping them deal with academic difficulties and achieving favorable educational results. The psychological and environmental factors like teacher support, goal orientation, learning environment, and test anxiety management play an essential role in affecting the resilience of students. This research paper seeks to predict the learning environment with the help of machine learning methods, taking into consideration the relationships between teacher support, goal orientation, test anxiety management, and student academic resilience. A dataset containing 70 observations of students was created by applying five educational variables including Teacher Support (TS), Goal Orientation (GO), Learning Environment (LE), Test Anxiety Management (TAM), and Student Academic Resilience (SAR). The two regression machine learning models employed in the prediction of the learning environment are linear regression and support vector regression (SVR). The R-squared value attained in the training stage for the linear regression is 0.8344, while the one attained in the testing stage is 0.8951. Conversely, the R-squared value for the support vector regression is 0.8827 and 0.8875 at the training and testing stages respectively. Prediction errors were low, and generalization accuracy was high for both. In the correlation analysis, there was very high correlation among all the variables examined in the research, particularly between teacher support and academic resilience of the learners.

Zitieren

APA

Kumari, G. (2026). Machine Learning-Based Prediction of Academic Resilience, Self-Concept, and Self-Efficacy. Contemporaneity of English Language and Literature in the Robotized Millennium, 76. https://doi.org/10.46632/cellrm/5/2/10

Vancouver

Kumari G. Machine Learning-Based Prediction of Academic Resilience, Self-Concept, and Self-Efficacy. Contemporaneity of English Language and Literature in the Robotized Millennium. 2026:76. doi:10.46632/cellrm/5/2/10

BibTeX
@article{Kumari2026,
  author = {Kumari, Gunjan},
  title = {Machine Learning-Based Prediction of Academic Resilience, Self-Concept, and Self-Efficacy},
  journal = {Contemporaneity of English Language and Literature in the Robotized Millennium},
  year = {2026},
  pages = {76},
  doi = {10.46632/cellrm/5/2/10}
}
Kostenlos starten →