Klasifikasi Genre Buku Berdasarkan Sinopsis Menggunakan Naïve Bayes dan Logistic Regression

Abstract

Genre is an important element in book categorization based on specific content characteristics or themes. However, manual classification processes are no longer efficient due to the increasing volume of literature. This study aims to compare the performance of Naïve Bayes and Logistic Regression algorithms in book genre classification based on synopses. The dataset used is secondary data obtained from Kaggle. The dataset consists of 4,535 samples after the preprocessing stage, with feature representation using the TF-IDF method. To address class distribution imbalance, the Synthetic Minority Over-sampling Technique (SMOTE) was applied. The evaluation was conducted using accuracy, precision, recall, and F1-score metrics. The experimental results show that Logistic Regression achieved the best performance with 75.19% accuracy and 75.16% F1-score, while Naïve Bayes achieved 72.22% accuracy and 72.11% F1-score. Based on this evaluation, Logistic Regression is considered more effective in classifying book genres from synopsis text.