AI powered book recommendation system

Abstract

The purpose of this study is to demonstrate the development of book recommendation systems through the usage of Artificial Intelligence (AI). Models of recommender systems displayed in the study are popularity-based, correlation-based (otherwise known as collaborative filtering), and content-based. Another type implemented in this study is the Lexile recommender, which suggests books based on similar Lexile levels. For the dataset, the researcher used a sample of books and user information from the public site Goodreads. The target audience for these books in the sample was high school students. As prior research shows that there is no single best way to create reading lists for students, the results of this study would encourage both leisure and educational reading to these students and allow readers to be able to create reading lists of their own that are personalized to their preferences. The researcher used Python libraries to implement these recommender structures. The results of this study showed that creating recommendation systems through AI was successful, but there is still much room for improvement in the complexity of these structures.