Music Recommendation Based on Literary Preferences in Artificial Intelligence

While being different forms of art, literature and music are similar in being able to convey symbolism, narrative and emotion. This paper explores the design and implementation of a music recommendation system in the context of a book and reading progress tracking web application. At the center of this work lies the question: How well can artificial intelligence find similarities between books and musical pieces and establish connections between them based on their symbolism? The main objective is to provide an answer to this question, by leveraging natural language processing algorithms. Numerous such algorithms have been implemented in music streaming applications, with the goal of recommending songs based on the user's listening preferences. However, the topic of music recommendations based on other arts or abstract human interests using artificial intelligence remains only briefly touched. This research aims to explore and extend this field, by employing techniques meant to provide relevant music suggestions stemming from literary tastes and to demonstrate the capacity of an artificial intelligence model to make accurate recommendations, by establishing connections between the semantic meanings and conveyed feelings of book snippets and song lyrics. Lastly, this work intends to contribute to the field of natural language processing in artificial intelligence, by bridging the gap between two prominent cultural arts in this day and age, by building an exploration base for correlating music with other forms of art.