Song Recommendation System using TF-IDF Vectorization and Sentimental Analysis
B Venkata Sai Chirasmayee · International Journal for Research in Applied Science and Engineering Technology · 2022
Abstract: In this project, we will build a machine learning model that recommends songs based on the songs already present in the playlist. We will implement Content based recommendation system. We will also create a web page in which the user can give the public playlist URI as input, and we will provide 5 to 20 song recommendations. Each song recommendation will be a link to the song and the song can be played on Spotify. Developers are now able to access millions of songs and obtain information like the song’s genre, the artist’s name, song’s release date, album name and so on through the Spotify API A developer can obtain can build Machine Learning models using the Spotify API using secret key and client id specific to the developer. We will be using spotipy package for Authentication of Spotify Developer credentials and for accessing the songs data. We will be using python scikit learn module for building Machine learning model. Flask module is used for web development. The final output will be a website deployed on local host