Your browser doesn't support javascript.
Predicting Antecedents of Employee Smart Work Adoption Using SEM-Multilayer Perceptron Approach
Human Behavior & Emerging Technologies ; : 1-9, 2023.
Article in English | Academic Search Complete | ID: covidwho-2194251
ABSTRACT
The COVID-19 pandemic forced many organizations to move to telework and smart work (SW), and this practice is expected to continue even later in the postpandemic period. Hence, it is very important for managers and organizations to identify the motivating and deterrent factors in adopting smart work and plan to manage them. Therefore, the present study using an innovative methodology tried to identify and prioritize the factors influencing employee SW adoption. In the first stage, the conceptual model of the research was designed, inspired by the literature. In the next step, using structural equation modeling (SEM), antecedents whose effects on employee SW adoption were confirmed were identified. Finally, the output of the SEM model was considered as the input of the multilayer perceptron (MLP) model, which is an artificial neural network model, to determine the importance of each antecedent in the prediction of employee behavior. The present study provides quantitative empirical evidence that perceived value, institutional and technological support, perceived limited communication, and perceived cost are antecedents of employee SW adoption that are, respectively, important in predicting the behavioral intentions of employees in acceptance of SW. The findings of this study contribute to both the SW and the behavioral intention theory literature. [ FROM AUTHOR]

Full text: Available Collection: Databases of international organizations Database: Academic Search Complete Type of study: Prognostic study Language: English Journal: Human Behavior & Emerging Technologies Year: 2023 Document Type: Article

Similar

MEDLINE

...
LILACS

LIS


Full text: Available Collection: Databases of international organizations Database: Academic Search Complete Type of study: Prognostic study Language: English Journal: Human Behavior & Emerging Technologies Year: 2023 Document Type: Article