This project utilizes advanced natural language processing (NLP) techniques to analyze movie metadata, leveraging Word2Vec models for semantic analysis. Through this approach, we generate meaningful embeddings for movies based on their titles, genres, and tags, enabling us to recommend movies by discovering semantic content similarities.

All the code, from data preprocessing to model implementation, can be found in Jupyter notebook included in this repository. It guides you through every step of the project.

The data set used can be found here: MovieLens dataset
The pre-trained vectors can be found here: Google Word2Vec

I hope you find this project insightful, or even serves as a valuable resource for anyone interested in the intersection of NLP and recommender systems!