Big-Data Analytics of Glassdoor Employee Reviews for Predicting Workforce Attrition in the Telecommunications Sector

Abstract

Employee attrition is a critical issue for telecom companies, leading to loss of talent, higher recruitment costs, and organizational instability. This study investigates the potential of using big-data scraping techniques on reviews to predict employee attrition in telecom firms. Leveraging advanced machine learning algorithms, this research builds predictive models to identify early warning signals of employee turnover. By extracting and analyzing large-scale reviews and sentiment data from , we aim to uncover patterns that indicate dissatisfaction, disengagement, and the likelihood of employees leaving their firms. The results reveal key factors such as workplace culture, management practices, and career development opportunities as significant predictors of attrition. Our findings suggest that sentiment analysis and text mining can provide telecom firms with actionable insights to reduce attrition and enhance employee retention. This study adds value by demonstrating the practical applications of big data in human resource management, offering a novel tool for predicting employee behavior in the telecom sector. The research concludes with recommendations for telecom companies to integrate sentiment analysis into their employee retention strategies.

Keywords: Big data, employee attrition, telecom firms, reviews, machine learning, sentiment analysis, employee retention.