Scholarlink

<p>The effects of the COVID-19 pandemic on people’s physical and mental health led to shifts in many employees’ psychological states, especially in organizations and privately owned enterprises that faced several challenges under the pandemic’s unusual circumstances. COVID-19 impacts people not just physically but also emotionally and psychologically, affecting their employment and overall well-being. As a result, this paper presented an Evolutionary Artificial Neural Network (E-ANN) architecture to forecast professional burnout syndrome among IT professionals during the COVID-19 era. The study specifically examines the influence of workload, social support, and autonomy on the mental and physical health status (MPHS) of IT professionals. To provide an accurate prediction, data is gathered, notably the demographic information of different personnel, and questionnaires were created and psychometrically validated through reliability and validity analysis. Cronbach’s alpha ( <InlineEquation ID="IEq1"> <EquationSource Format="TEX">\(\:\alpha\:=0.89)\)</EquationSource> </InlineEquation> overall and exploratory factor analysis (KMO = 0.89, <i>p</i> &lt; .001). The SPSS software performed the statistical analysis using the data. An innovative EANN that combines the ANN model and the Seagull Optimization Algorithm is proposed to evaluate the performance of the models. The proposed approach attained an improved Accuracy of about 97% which results in the superior performance of the model in comparison to the current models, such as ANN, SVM, KNN, and Decision Tree models. The results revealed that workload, social support, and autonomy significantly affect mental and physical health status (MPHS) among IT professionals. These findings confirm both statistical and predictive validity, reinforcing the robustness of the proposed model. Therefore, the E-ANN-SOA hybrid model supports a very reliable predictive framework in which an organization would conduct an early diagnosis of the risk posed by burnout, thus establishing preventive and supportive strategies directed toward enhancing employee well-being and work productivity.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Prediction of professional burnout syndrome among it professionals during the COVID-19 era using evolutionary artificial neural network

  • 期刊论文

  • 发表日期：

    2026年1月31日

查看全文
  • S. Sivakami,
  • T. S. Sasikala

摘要

The effects of the COVID-19 pandemic on people’s physical and mental health led to shifts in many employees’ psychological states, especially in organizations and privately owned enterprises that faced several challenges under the pandemic’s unusual circumstances. COVID-19 impacts people not just physically but also emotionally and psychologically, affecting their employment and overall well-being. As a result, this paper presented an Evolutionary Artificial Neural Network (E-ANN) architecture to forecast professional burnout syndrome among IT professionals during the COVID-19 era. The study specifically examines the influence of workload, social support, and autonomy on the mental and physical health status (MPHS) of IT professionals. To provide an accurate prediction, data is gathered, notably the demographic information of different personnel, and questionnaires were created and psychometrically validated through reliability and validity analysis. Cronbach’s alpha ( \(\:\alpha\:=0.89)\) overall and exploratory factor analysis (KMO = 0.89, p < .001). The SPSS software performed the statistical analysis using the data. An innovative EANN that combines the ANN model and the Seagull Optimization Algorithm is proposed to evaluate the performance of the models. The proposed approach attained an improved Accuracy of about 97% which results in the superior performance of the model in comparison to the current models, such as ANN, SVM, KNN, and Decision Tree models. The results revealed that workload, social support, and autonomy significantly affect mental and physical health status (MPHS) among IT professionals. These findings confirm both statistical and predictive validity, reinforcing the robustness of the proposed model. Therefore, the E-ANN-SOA hybrid model supports a very reliable predictive framework in which an organization would conduct an early diagnosis of the risk posed by burnout, thus establishing preventive and supportive strategies directed toward enhancing employee well-being and work productivity.