MoodSense a Browser Based Ensemble Sentiment Analysis System for Real Time Mood Tracking

We present MoodSense, an open-source mood-tracking system that combines three complementary sentiment analysis models — DistilBERT, VADER, and TextBlob — into a unified Wellbeing Score. Unlike prior tools that require server infrastructure or specialist hardware, MoodSense runs entirely in the browser as a Progressive Web App with no installation required, and is additionally available as a Google Colab notebook for researchers. The system achieves 90.6% accuracy on the SST-2 benchmark, a 23.7 percentage point improvement over VADER alone, and a Spearman correlation of 0.566 against emotion-valence proxy labels. A built-in crisis keyword detector and an Anthropic Claude-powered conversational companion make MoodSense one of the first fully open-source tools to integrate ensemble NLP with conversational AI support in a single deployable browser application. We describe the system architecture, benchmark evaluation, and ablation study, and release all code publicly.