Copyright © 2025 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{175912,
        author = {Lakshana S and Janani M and Jeevashri D and Kalaiselvi S},
        title = {HUMAN SIGNALS: ANALYZING WORKPLACE BEHAVIOURS TO DECODE SENTIMENTS},
        journal = {International Journal of Innovative Research in Technology},
        year = {2025},
        volume = {11},
        number = {11},
        pages = {4352-4357},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=175912},
        abstract = {Employee well-being is vital for organizational success, yet traditional performance reviews fail to capture real-time emotional and behavioral insights. This study proposes an ML-based Employee Tracker System using Random Forest, XGBoost Regressor, VADER, and Likert-scale analysis to assess engagement, productivity, and emotional states. Attendance, communication logs, and survey responses are analyzed for a holistic emotional profile. XGBoost Regressor predicts project completion, Random Forest Classifier evaluates attendance, and VADER performs sentiment analysis on emails and chats. Survey feedback is classified using a Likert-based model. Final emotion classification fuses all analysis results. The system ensures GDPR compliance via anonymization and restricted data access. Tested on real and synthetic datasets, it achieved high accuracy in sentiment detection, project tracking, and attendance analysis, offering actionable insights for proactive HR decision-making},
        keywords = {Survey-based Emotion Classification, Machine Learning (ML), Natural Language Processing (NLP), Sentiment Analysis, GDPR Compliance.},
        month = {April},
        }