rasbt/musicmood
A machine learning approach to classify songs by mood.
Extracts song lyrics from the Million Song Dataset and applies text classification to predict binary mood labels (happy/sad), comparing Naive Bayes and Random Forest approaches with feature engineering including whitelist-based word filtering. Includes a live web application for real-time mood prediction and comprehensive Jupyter notebooks documenting data collection, exploratory analysis, and model training workflows.
423 stars. No commits in the last 6 months.
Stars
423
Forks
108
Language
OpenEdge ABL
License
GPL-3.0
Category
Last pushed
Nov 02, 2016
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/rasbt/musicmood"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related frameworks
hoangsonww/Moodify-Emotion-Music-App
🎹 Moodify - an emotion-based music recommendation system that uses AI/ML models to analyze text,...
aj-naik/Emotion-Music-Recommendation
Flask web app for recommending music based on your facial expressions using FER 2013 dataset and...
adblockradio/adblockradio
An adblocker for live radio streams and podcasts. Machine learning meets Shazam.
Sandlie101G12B/Lost
The best open source music player on Android.
CharlesYuan02/emotion-music-player
A music player that recommends songs based on your detected mood. Created for TOHacks 2021.