Designing a Movie Recommendation System Through a Transformer-Based Embeddings Space

Artificial intelligence has found a critical use in recommender systems, especially in the film industry. Recommender systems have attracted a lot of attention due to their capacity to completely alter user experiences in a variety of domains. This paper proposes a relevant movie recommender system emphasizing the role of transformers in converting natural language text inputs, which describe movie features, into processable embeddings. These embeddings were put through a procedure of dimensionality reduction to graph the movies according to their features. By doing this, we could visualize the nature and behavior of the movies during a CBR recommendation process.