Year: 2025
Type: article
Abstract: One helpful tool for book recommendations is a book summary. This article discusses categorizing books only on the basis of their title and summary, without taking into account the author’s background or place of origin. The title and abstract of the book make reference to the machine learning methods used to create the genre. This study assesses the capacity to distinguish between books based on their title and summary using four machine learning models. The dataset that can be found on the Kaggle website includes 10 distinct genre kinds and 4657 instances. The dataset is first subjected to exploratory data analysis, and then a machine learning based strategy is used to extract features from the book’s title and abstract using natural language processing techniques. We use 80 % of the samples (3,726 instances) to train the models, and the remaining 20 %(931 instances) are used for testing. Every model’s performance is evaluated using a range of metrics, including accuracy, precision, recall, and F1score. The method also determines which words are most frequently used in each genre. Systems for automatically classifying books and making recommendations can be built using this framework.
DOI: 10.14429/djlit.20026
Author: Jhimli Adhikari
Institution: Narayan Medical College and Hospital
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: diamond
OpenAlex ID: W4410906998