Forecasting Job Burnout among University Faculty Members of Yazd Payame Noor University Using Artificial Neural Network Technique

Abstract

Background: Faculty members are one of the main factors in the higher education system, that high level of occupational stress caused by educational, research, and executive duties makes them exposed to burnout. The purpose of this study was predicting burnout of faculty members of Yazd Payame Noor University using artificial neural network technique. Methods: The present research was descriptive in terms of method, and applied in terms of purpose. The statistical population of this research was the faculty members of Yazd Payame Noor University. The analysis was performed on 315 data from 105 faculty members that were acquired during the last three academic years. Data were collected using two closed questionnaires. Data were analyzed using SPSS software version 22. For analysis of data, including 23 independent variables and one dependent variable, two types of neural network, including MLP and RBF were designed and implemented. Results: Correct percent of burnout prediction in the training, testing and validation data for the MLP neural network was 83.3, 80.9 and 74.5, respectively, and for the RBF neural network was 73.1, 93.3 and 9.76, respectively. The area under the rock for MLP and RBF networks was 0.823 and 0.833, respectively. Conclusion: Comparison of two MLP and RBF neural networks based on rock curve and prediction correct percent showed that the RBF neural network is more effective in forecasting job burnout of faculty members of Yazd Payame Noor University, and the variables scientific group, teaching master students, age and communication had the greatest impact on burnout.