A Sensitive Analysis for Teacher Burnout Identification using Machine Learning Method: Jordan Case Study

Accurate prediction is crucial for research and decision-making, particularly in understanding and addressing burnout, which stems from prolonged emotional, physical, and mental stress, often associated with one’s occupation. This phenomenon, prevalent among high-achieving individuals like teachers, entails a sense of diminished accomplishment and personal identity. Teachers, confronted with diverse challenges such as class size, the frequency of classes per week, the salary rate, and more, are susceptible to burnout. This study addresses this issue by administering the Maslach Burnout Inventory to a sample of 500 Jordanian teachers and employing a hybrid machine-learning algorithm to predict burnout levels. The model undergoes evaluation through Python programming, where its performance is measured against key metrics including Accuracy, R<sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sup> (Coefficient of Determination), MAE (Mean Absolute Error), and RMSE (Root Mean Square Error). The effect of this implication is that it emphasizes the significance of prediction which in turn can help to reduce the negative effects of burnout on the workforce and also ought to provide data-driven interventions that are geared towards improvement of the working conditions and minimization of the turnover rates. This entails that the data brings into question the relative condition of teachers to Academic Qualification, Marital Status, Age, Years of Experience, and Teachers’ Salary Scale is as important as and is capable of delivering accurate prediction of burnout levels underscored by integration of Maslach Burnout Inventory evaluation questions.