Article Per Year (5 Year)
p-Index From 2021 - 2026
0.23
P-Index
This Author published in this journals
All Journal Jurnal Nasional Teknologi Informasi dan Aplikasinya
I Made Treshnanda Mas
Unknown Affiliation
Computer Science & IT Engineering

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

Found 1 Documents
Search

 1 
Aspect Based Sentiment Analysis Terhadap Ulasan Produk Skincare di E-Commerce Menggunakan CNN-LSTM I Made Treshnanda Mas; Anak Agung Istri Ngurah Eka Karyawati
Jurnal Nasional Teknologi Informasi dan Aplikasinya Vol. 3 No. 2 (2025): JNATIA Vol. 3, No. 2, Februari 2025
Publisher : Informatics Department, Faculty of Mathematics and Natural Sciences, Udayana University

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24843/JNATIA.2025.v03.i02.p05

Abstract

Skincare product is any type of formulation intended to be topically applied with the intention of improving skin appearance, texture, or health. The burgeoning skincare product market in Indonesia, particulary in E-Commerce, underscores a shift towards online purchasing habits. With platforms like Shopee, Tokopedia, and Lazada dominating, user reviews play a pivotal role when making decision. However the sheer volume of reviews necessitates efficient processing methods. Aspect Based Sentiment Analysis (ABSA) emerges as a solution, delving deeper into sentiment analysis by identifying specific aspects within user feedback. Previous studies have shown Convolutional Neural Network based algorithms to have high performance in similar contexts. In this study, the author used CNN mixed with Long Short Term Memory (LSTM) alongside Term Frequency-Inverse Document Frequency (TF-IDF) and Bag of Words (BoW) as feature selection techniques to classify aspects into 5 classes and sentiment into 2 classes. The result of aspect classification produced accuracy, precission, recall, and F1-Score of 87.3%, 87%, 87%, and 85.9%. Meanwhile sentiment classification produced accuracy, precission, recall, and F1-Score of 87%, 87%, 87%, and 87% 
Co-Authors Anak Agung Istri Ngurah Eka Karyawati