Hybrid Machine Learning and NLP Approaches for Sentiment Productivity Analysis of Employees

Deepthi M. Pisharody; Anjali E.S; Maidhili Mohan K

doi:https://doi.org/10.14445/22312803/IJCTT-V73I6P113

Research Article | Open Access | Download PDF

Volume 73 | Issue 6 | Year 2025 | Article Id. IJCTT-V73I6P113 | DOI : https://doi.org/10.14445/22312803/IJCTT-V73I6P113

Hybrid Machine Learning and NLP Approaches for Sentiment Productivity Analysis of Employees

Deepthi M. Pisharody, Anjali E.S, Maidhili Mohan K

Received	Revised	Accepted	Published
30 May 2025	04 Jun 2025	20 Jun 2025	30 Jun 2025

Citation :

Deepthi M. Pisharody, Anjali E.S, Maidhili Mohan K, "Hybrid Machine Learning and NLP Approaches for Sentiment Productivity Analysis of Employees," International Journal of Computer Trends and Technology (IJCTT), vol. 73, no. 6, pp. 104-111, 2025. Crossref, https://doi.org/10.14445/22312803/IJCTT-V73I6P113

Abstract

The active involvement and well-being of employees have an immense effect on organizational productivity. However, traditional review procedures for employee engagement often rely on manual analysis of qualitative feedback, which makes them ineffective and biased. In order to improve the precision and effectiveness of employee assessments, this study suggests an automated framework that combines Machine Learning (ML) and Natural Language Processing (NLP). The system associates the structured performance and the attendance data with textual feedback submitted by employees to show a comprehensive analysis of employee happiness. Prior to TF-IDF vectorisation, text data is pre-processed using common NLP techniques like tokenisation, stemming, and stop-word removal. To sort out the feedback as positive, neutral, or negative, we have used machine learning models such as Random Forest, Naïve Bayes, Support Vector Machine (SVM), and Logistic Regression. Logistic Regression outperformed other machine learning models with an accuracy of 99.01%. Clustering of employees is performed according to the key performance indicators using the K-Means clustering algorithm, which opens up the trends in organizational productivity and employee engagement. The suggested system aligns with modern methodologies that support a comprehensive perspective of employee feedback by integrating sentiment classification, predictive modeling, and clustering into a single pipeline. Linking clustered behaviours to productivity and attendance trends goes beyond simple sentiment polarity and enables organizations to pinpoint not only disgruntled individuals but also systemic problems across departments.

Keywords

Artificial Intelligence, K-means clustering, Natural Language Processing, Machine Learning, Employee happiness.

References

[1] Bing Liu, “Sentiment Analysis and Opinion Mining,” Computational Linguistics, vol. 5, no. 1, pp. 511-513, 2012.
[CrossRef] [Google Scholar] [Publisher Link]
[2] Juan Ramos, “Using TF-IDF to Determine Word Relevance in Document Queries,” Proceedings of the First International Conference on Machine Learning, vol. 242, pp. 133-142, 2003.
[Google Scholar]
[3] Bo Pang, Lillian Lee, and Shivakumar Vaithyanathan, “Thumbs Up? Sentiment Classification Using Machine Learning Techniques,” arXiv:cs/0205070, pp. 1-9, 2002.
[CrossRef] [Google Scholar] [Publisher Link]
[4] J. MacQueen, “Some Methods for Classification and Analysis of Multivariate Observations,” Proceedings of the Fifth Berkeley Symposium on Mathematical Statistics and Probability, vol. 5, no. 1, pp. 281-297, 1967.
[Google Scholar]
[5] Ian T. Jolliffe, and Jorge Cadima, “Principal Component Analysis: A Review and Recent Developments,” Philosophical Transactions of the Royal Society A: Mathematical, Physical and Engineering Sciences, vol. 374, no. 2065, pp. 1-16, 2016.
[CrossRef] [Google Scholar] [Publisher Link]
[6] Charu C. Aggarwal, and ChengXiang Zhai, “A Survey of Text Classification Algorithms,” Mining Text Data, pp. 163-222, 2012.
[CrossRef] [Google Scholar] [Publisher Link]
[7] Fabrizio Sebastiani, “Machine Learning in Automated Text Categorization,” ACM Computing Surveys, vol. 34, no. 1, pp. 1-47, 2002.
[CrossRef] [Google Scholar] [Publisher Link]
[8] Thomas G. Dietterich, “Ensemble Methods in Machine Learning,” Multiple Classifier Systems, pp. 1-15, 2000.
[CrossRef] [Google Scholar] [Publisher Link]
[9] Marina Sokolova, and Guy Lapalme, “A Systematic Analysis of Performance Measures for Classification Tasks,” Information Processing & Management, vol. 45, no. 4, pp. 427-437, 2009.
[CrossRef] [Google Scholar] [Publisher Link]
[10] Martin R. Edwards, Kirsten Edwards, and Daisung Jang, Predictive HR Analytics: Mastering the HR Metric, Kogan Page Publishers, 2019.
[Google Scholar] [Publisher Link]
[11] S. Ranjit Kumar, “Sentiment Analysis on Employee Layoffs Based on Hybrid Feature Extraction and Long Short Term Memory Network,” International Journal of Natural Language Processing, vol. 2, no. 1, pp. 12-20, 2024.
[Publisher Link]