Article Per Year (5 Year)
p-Index From 2020 - 2025
0.23
P-Index
This Author published in this journals
All Journal Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer
Dhiva Mustikananda
Fakultas Ilmu Komputer, Universitas Brawijaya
Computer Science & IT Control & Systems Engineering Education Electrical & Electronics Engineering Engineering

Published : 1 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 1 Documents
Search

 1 
Perbandingan Algoritma Naive Bayes dan Support Vector Machine untuk Analisis Sentimen terhadap Review Produk Aster Kosmetik Malang Marketplace Shopee Dhiva Mustikananda; Dian Eka Ratnawati; Bayu Rahayudi
Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer Vol 6 No 7 (2022): Juli 2022
Publisher : Fakultas Ilmu Komputer (FILKOM), Universitas Brawijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

Aster Cosmetics Malang is a popular beauty shop in Malang City. Aster Cosmetics uses the Shopee online shopping platform as a product promotion medium. Online shopping provides many conveniences in the midst of the COVID-19 pandemic. On the online shopping platform there is a feature to add product reviews, where product reviews can be used as a consideration for potential buyers in making decisions. Shopee is used as a data source for sentiment analysis on Aster Cosmetics Malang product reviews. The review data are classified into positive, negative, and neutral categories. Classification is done by comparing the Naive Bayes algorithm and Support Vector Machine. This study uses 300 data for the classification of 3 sentiments, namely positive, negative, and neutral, then 200 data for the classification of 2 sentiments, namely positive and negative. Testing by comparing the two methods using the same test parameters, namely the percentage of training data and test data 80%:20% and cv=10. The classification results get the highest accuracy value of the Support Vector Machine method in the classification of 2 sentiments with an accuracy value of 87.56%, precision 88.81%, recall 86.76% and f-measure 86.85%, the highest accuracy results in the classification of 3 sentiments using the Support Vector Machine method with an accuracy value of 79.71%. , precision 81.56%, recall 79.56% and f-measure 79.36%.
Co-Authors Bayu Rahayudi Dian Eka Ratnawati