SENTIMENT ANALYSIS OF TOKOPEDIA PRODUCT REVIEWS USING THE NAÏVE BAYES CLASSIFIER ALGORITHM: CASE STUDY OF PENGRAJIN.COM SHOP

AULIA, MUHAMMAD (2024) SENTIMENT ANALYSIS OF TOKOPEDIA PRODUCT REVIEWS USING THE NAÏVE BAYES CLASSIFIER ALGORITHM: CASE STUDY OF PENGRAJIN.COM SHOP. Tugas Akhir thesis, Informatics.

[img] Text
5200411482_MUHAMMAD AULIA_Abstrak.pdf
Download (16kB)

Abstract

ABSTRACT This research employs the Naïve Bayes Classifier with the SMOTE and Imblearn algorithms to address class imbalance in the product review dataset on Tokopedia. The Naïve Bayes Classifier is a theorem-based algorithm with the assumption of independent features. SMOTE generates synthetic samples for negative reviews, while Imblearn increases the number of samples in the minority class, enhancing sentiment analysis accuracy. The objective is to analyze product sentiments on Tokopedia, understand public opinions on Toko Pengrajin.com, and provide insights to the company for improving product and service quality. The results indicate that the Naïve Bayes Classifier with SMOTE and Imblearn achieves an accuracy of 87%, surpassing the accuracy without these methods. This underscores the effectiveness of the Naïve Bayes Classifier algorithm in product sentiment analysis on Tokopedia, particularly for Toko Pengrajin.com. The SMOTE and Imblearn methods also contribute significantly to addressing class imbalance, thereby improving sentiment analysis accuracy. The findings of this research provide valuable information for the company to enhance product and service quality based on public feedback through sentiment analysis. Keywords: Naïve Bayes Classifier, SMOTE, Sentiment Analysis, Pengrajin.com, Tokopedia

Item Type: Thesis (Skripsi, Tugas Akhir or Kerja Praktek) (Tugas Akhir)
Subjects: T Technology > T Technology (General)
Divisions: Fakultas Sains Dan Teknologi > S1 Informatika
Depositing User: Kaprodi S1 Informatika UTY
Date Deposited: 08 Aug 2024 01:27
Last Modified: 08 Aug 2024 01:27
URI: http://eprints.uty.ac.id/id/eprint/15894

Actions (login required)

View Item View Item
UTY Open Access is powered by EPrints 3 which is developed by the School of Electronics and Computer Science at the University of Southampton. More information and software credits.