The proliferation of digital commerce has generated unprecedented volumes of customer feedback that cannot be manually processed at scale. This paper presents SentimentAI, a comprehensive AI-powered customer sentiment analysis dashboard that automates the acquisition, processing, classification, and visual representation of customer feedback in real time. The system implements a hybrid natural language processing pipeline combining VADER (Valence Aware Dictionary and sEntiment Reasoner) for sentiment polarity classification, a rule-based emotion detection module supporting five emotional categories, TextBlob-powered keyword extraction, and an automated contextual response generator. Built using Python, Django 4.2, and SQLite3, the application follows the Model-View-Template architecture and supports two user roles: customers who submit feedback through a simulated ecommerce storefront, and administrators who access an intelligence dashboard with sentiment distribution charts, keyword frequency analysis, negative feedback alerts, and AI-generated business insights. The system is deployed on Vercel cloud platform, demonstrating production readiness. Experimental evaluation confirms that the hybrid approach accurately classifies sentiment polarity and generates contextually appropriate automated responses, transforming unstructured textual feedback into structured, actionable business intelligence.
Sree et al. (Thu,) studied this question.