Letterboxd Movie Ratings Data

This is scraped, publicly accessible Letterboxd ratings data, taken from the top 4000 users on Letterboxd in any given month. and creates a movie recommendation model with it that can generate recommendations when provided with a Letterboxd username. A user's "star" ratings are scraped from their Letterboxd profile and assigned numerical ratings from 1 to 10 (accounting for half stars). Movie data was enriched with data from the TMDB API.

The movie, user, and ratings tables here are exported from a Mongo database and each can be used to re-populate their respective collections in a local database for anyone who wants to build their own recommendations model/perform analysis without spending several hours re-scraping the data.

I put together a recommendation model for any Letterboxd user, based on this data which lives here: https://bit.ly/letterboxd-movie-recs

The Github repository for the crawler, recommendation model, and website, lives here: https://github.com/sdl60660/letterboxd_recommendations