Acervans/lastfm_RS

LastFM recommendation with sentiment analysis (Bachelor Thesis Project)

12
/ 100
Experimental

This project helps music enthusiasts explore new music by providing song recommendations that consider the emotional tone of music descriptions, album reviews, and other textual content related to artists and tracks. It takes your listening history and preferences (implicitly, through Last.FM data) and processes text using tools like the NRC-VAD Lexicon to suggest music that matches specific emotional qualities. The output is a personalized list of music recommendations, presented through the LastMood web application, for users looking to discover emotionally resonant songs.

No commits in the last 6 months.

Use this if you are a music lover or enthusiast who wants to discover new songs and artists based on the emotional sentiment expressed in their descriptions, rather than just popularity or genre.

Not ideal if you are looking for a plug-and-play music recommendation service with advanced deep learning models, as it requires local setup and only offers basic recommenders due to size constraints.

music-discovery personalized-recommendations sentiment-driven-curation music-taste-analysis emotional-music-search
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 4 / 25
Maturity 8 / 25
Community 0 / 25

How are scores calculated?

Stars

6

Forks

Language

Jupyter Notebook

License

Last pushed

Jan 21, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/nlp/Acervans/lastfm_RS"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.