EmotionMetrics: A CNN-Based Emotion Analytics Platform for Art-Assisted Student Well-being

Author(s)	Ms. Snehal Bhamare, Ms. Khushi Bedmutha, Ms. Akshada Pawar, Ms. Sharvari Pawar
Country	India
Abstract	EmotionMetrics is a multimodal platform based on CNN that uses affective computing, computer vision, and Mandala art therapy to evaluate and improve student emotional wellness. The platform combines facial expression analysis by means of a fine-tuned ResNet-50 model with Mandala color interpretation and self-reporting of emotional states. The system got more than 81% accuracy on the combined experimental evaluation of the FER-2013, RAF-DB, and CK+ datasets. The chatbot driven Mandala module uses psychological color mappings to interpret the colors selected and, thereby, provide qualitative results that are in line with the quantitative emotion detection. The information obtained is summarized into a Happiness Index, which is presented using a React.js dashboard with Node.js and MongoDB at the backend. EmotionMetrics blends AI and art-based therapy methods to provide an explainable, datacentric system for the continual monitoring and enhancement of emotional well-being in the learning settings.
Keywords	Emotion Detection, ResNet-50, Mandala Art Therapy, CNN, Emotion Recognition, Student Well-being, Data Visualization
Field	Engineering
Published In	Volume 8, Issue 5, September-October 2026
Published On	2026-09-08

About IJFMR Fees & Payment Current Issue Publication Archive	Submit Research Paper Track Submission Status Publication Guidelines Publication Ethics Peer Review & Plagiarism	Join as a Reviewer Editors & Reviewers Reviewer Referral Program Get Reviewer Membership Certi.	Website/Journal Policies Usage Policy Content Policies Privacy Policy

Contact Us		+91-9687-828-838	editor@ijfmr.com

International Journal For Multidisciplinary Research