Workplace Productivity Through Employee Sentiment Analysis Using Machine Learning

Abstract

Purpose: The objective of this study was to analyze workplace productivity through employee sentiment analysis using machine learning. Theoretical framework: A lot of literature is already published on employee productivity and sentiment analysis as a tool, but the study here is intended to address the issues in employee productivity post-COVID’19. Design/methodology/approach: The authors have studied the relationship between sentiments and workplace productivity post-COVID- 19. Sentiments were captured from the text inputs given by seventy-two survey respondents from a mid-sized consultancy firm and correlated against the productivity scores. A machine learning model was developed using Python to calculate the sentiment score. Findings: 98.6% of the respondents had a high productivity score, whereas 88.9% showed positive sentiments. The majority of the responses showed a positive correlation between positive sentiments and high productivity levels. Research, Practical and Social Implications: The study paves way for identification of action plan for productivity enhancement through sentiment analysis. Originality/Value: No previous work on employee productivity using sentiment analysis is done till now.