AI-DRIVEN APPROACHES TO PREDICTING EMPLOYEES’ JOB SATISFACTION FOR HR MANAGEMENT

Abstract

Job satisfaction can be defined as employees having positive attitudes toward their present roles within an organization. Some of the factors that play a significant role include engagement, empowerment, commitment, and support. The purpose of this research is to analyze how AI impacts the assessment of job satisfaction using tools such as sentiment analysis, surveys, and machine learning algorithms, which include emotion detection. In this paper, we consider how AI is used for predicting job satisfaction among employees and stress the significance of developing AI-powered systems responsibly to ensure fairness and well-informed decision-making during human resource management. The different machine learning algorithms used in AI-based HR have been reviewed, which include logistic regression, random forest classifier, KNeighbors classifier, Support Vector Classifier (SVC), and XGBClassifier. Logistic Regression was the most accurate algorithm in terms of predicting employee job satisfaction. We discuss the basics of Logistic Regression in AI-based HR systems as well as difficulties that arise in the development of such systems.