Evaluating bids

Api: Music recommendation on Spotify based on tweets (using Word2vec)

Published on the December 14, 2020 in IT & Programming

About this project

Open

I want to design a recommendation system that recommends user songs based on their tweets that use the hashtag #nowplaying. Initially, I wanted to weigh down their tweets and analyze word by word and see if they've tweeted anything ABOUT certain songs, but it seems like that will be taking more time for me.

Just for reference, I will provide a brief idea of the system below. Feel free to comment or give your thoughts on them.

1. User will give access to their Spotify account using the API.
2. Prompt user to log in or if the account is public, they can just input their Twitter username.
3. Twitter's API will run a search for #nowplaying on their account (tweets).
4. Analyze the tweet that has the hashtag and extract the song title from the tweets and pass the data to Spotify API to analyze.
5. Find the extracted song on Spotify using the Spotify API.
6. Based on that song, the API will provide 10-20 songs related to be compiled into a playlist for the user.
7. Once the songs have been compiled into a playlist, the system will show the user the song recommendations, and the user will have the option to save it to their account or discard it.

Project overview

I have written step 3-5, but within the three steps, I've only been using Spotify's console features. I would like to also use the word2vec function because the Spotify console is very limited when it comes to longer tweets. I have close to zero experience working with API, but I have some experience working with few languages like Java, Python.

Category IT & Programming
Subcategory Web development
What is the scope of the project? Medium-sized change
Is this a project or a position? Project
I currently have I have specifications
Required availability As needed
API Integrations Social media (Facebook, Twitter, etc.)
Roles needed Developer

Delivery term: December 18, 2020

Skills needed