Machine Learning Powered Genre Prediction for Next Level Book Recommendations
Anitha Julian, B. Pavithra · 2024
The proposed work delves into how recommender systems, like those on YouTube and Amazon, shape our online experiences, particularly in book recommendations. It addresses the challenge of the “cold start problem” with the help of a Popularity-based recommender initially, adapting to personalized suggestions through Collaborative Filtering as users engage. This dual approach aims for a comprehensive system that overcomes challenges in new user on boarding and adapts to evolving preferences. The importance of continuous evaluation is emphasized for ongoing effectiveness. In a separate study, the research explores the application of Natural Language Processing (NLP) in predicting book genres. It uses algorithms to analyze textual data, employing techniques like Exploratory Data Analysis (EDA) to uncover patterns. The modeling phase involves text classification algorithms, contributing to a deeper understanding of genre prediction through the application of NLP techniques.