الفهرس 
الفصل الثاني: الإطار النظري والدراسات السابقة ذات الصلةيوجد فقط 14 صفحة متاحة للعرض العام
 |  | from | 105 |  |  |
| | | from | 105 | | |
المستخلص
Abstract
The current study aimed to verify the effectiveness of using machine learning algorithms and compare them with traditional statistical methods by predicting the academic performance of a sample of second-level students at the Faculty of Education, Ain-Shams University (n = 472) in the academic year 2022-2023, considering some psychological variables (emotional intelligence, cognitive test anxiety, and general self-efficacy) in addition to previous academic performance and discipline. The following scales were applied: the emotional intelligence scale, the cognitive test anxiety scale, and the general self-efficacy scale. The results indicated that the linear regression model is the least predictive in quality compared to other models (R 2 = 0.135, RMSE = 0.423), and in contrast, the artificial neural network model was the best (R 2 = 0.266, RMSE = 0.390). The relative importance of the predictor variables was calculated according to the artificial neural network model by using the permutation method.