HN Showcase
Back to browse
MoodSense AI – mood detection and recommendations from text

MoodSense AI – mood detection and recommendations from text

by aman179102·Apr 11, 2026·2 points·0 comments
Visit ProjectView on HN

AI Analysis

●MidShip It

Text sentiment analysis when IBM Watson and Google NLP already dominate this space.

Strengths
  • •FastAPI backend with Gradio UI means both programmatic and interactive access.
  • •Probability distribution output shows model confidence, not just labels.
Weaknesses
  • •Standard scikit-learn + LightGBM pipeline with no novel architecture or fine-tuning approach.
  • •No differentiation from established sentiment analysis APIs with better accuracy.
Category
AI/ML
Target Audience

Developers learning NLP, hobbyists building mood tracking apps

Similar To

IBM Watson Tone Analyzer · Google Cloud Natural Language · Azure Text Analytics

Post Description

Built MoodSense AI, an NLP project that detects mood from text and provides simple recommendations.

It classifies input into multiple moods, shows confidence and probability distribution, and includes both an API and UI.

The goal was to move beyond just training a model and build something usable.

Source: https://github.com/aman179102/moodsense-ai

Feedback is welcome.

Similar Projects