Emotion-Aware Mental Health Chatbot

Heramb Vengurlekar Thadomal Shahani Engineering College vengurlekarheramb19@gmail.com

Keywords: RoBERTa, NLP, GoEmotions, React, Flask, Node.js

Overview

An empathetic conversational AI system that detects nuanced user emotions and dynamically conditions LLM response generation to provide supportive, context-aware interactions.

Architecture & Technical Highlights

  1. Emotion Classification: Fine-tuned RoBERTa on the multi-label GoEmotions dataset to capture subtle emotional cues beyond binary sentiment.
  2. Two-Stage Generation Pipeline: Decoupled classification from generation to prevent hallucinated emotional assumptions and maintain therapeutic guardrails.
  3. Full-Stack Microservices: React UI connected to Node.js backend, communicating via REST with a dedicated Flask inference microservice for real-time sentiment scoring.