Extreme Learning Machine Optimization for Employee Satisfaction With Modified Metaheuristic

In the contemporary business landscape, the success of a company is intricately linked to the engagement and satisfaction of its workforce. This study analyzes the signifi-cance of developing a contented and engaged employee base, emphasizing the direct impact of workplace satisfaction on productivity, turnover rates, and overall organizational dynamics. Organizational culture emerges as a pivotal factor influencing the recruitment, retention, and satisfaction of talented employees. To address the complexities of identifying and mitigating employee dissatisfaction, this research work proposes a comprehensive solution harnessing the capabilities of cloud-based technologies, specifically text mining, Natural Language Processing (NLP), and modified metaheuristic techniques. The study explores the application of an extreme learning machine as a classifier for assessing employee satisfaction within a cloud computing framework. Acknowledging the critical role of hyperparameter selection in model performance, metaheuristic optimizers and cloud platforms implementation are employed to enhance accu-racy and effectiveness. Furthermore, a novel modification to a metaheuristic algorithm for satisfying the unique requirements of this research is introduced. This research study demonstrates the efficiency of the optimized models, achieving an accuracy rate surpassing 84%. By integrating cloud computing technologies into the proposed framework, organizations gain a powerful and scalable tool for proactively identifying and addressing employee dissatisfaction, ultimately contributing to the improved employee well-being and organizational success in the cloud era.