Copyright © 2026 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{205218,
        author = {KSHIPRA SHRIPAD UPALEKAR and NUPUR SHEKHAR KULKARNI and PROF. TEJAS V. JOSHI},
        title = {MoodScope AI: An Explainable Human-Centered Framework for Employee Emotion Intelligence using ResNet18 and Graph Attention Networks},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {13},
        number = {1},
        pages = {5845-5855},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=205218},
        abstract = {Facial Emotion Recognition (FER) has emerged as a significant research area in affective computing, enabling automated analysis of human emotions through deep learning techniques. Despite substantial progress in recognition accuracy, many existing FER systems suffer from limited interpretability, making their decision-making processes difficult to understand and trust in real-world organizational environments. To address this challenge, this paper presents MoodScope AI, an explainable and human-centered framework for employee emotion intelligence. The proposed framework integrates ResNet18 for facial emotion recognition, Grad-CAM for visual explanation of model predictions, and Graph Attention Networks (GATs) for modeling relational emotional dynamics among employees. In addition, a real-time analytics dashboard is developed to visualize emotional trends, engagement patterns, and workplace wellbeing indicators. The framework is evaluated using benchmark FER datasets, including FER2013 and CK+, demonstrating strong emotion classification performance with an accuracy of 91.2%. Experimental results indicate that the integration of explainable AI and graph-based relational learning improves both transparency and analytical capability while maintaining computational efficiency. The proposed approach contributes toward the development of trustworthy, interpretable, and ethically aligned AI systems for intelligent workplace analytics and employee wellbeing assessment.},
        keywords = {Facial Emotion Recognition, Explainable Artificial Intelligence, Employee Emotion Analytics, Workplace Wellness Intelligence, ResNet18, Grad-CAM, Graph Attention Networks, Human-Centered AI, Real-Time Emotion Analysis, Affective Computing},
        month = {June},
        }