SENTIMENT ANALYSIS OF PT AMARTA LINTAS NUSANTARA USING THE LONG SHORT-TERM MEMORY (LSTM) METHOD
JOURNAL OF SCIENCE AND APPLIED ENGINEERING · 26.10.2026 · 9 (2) · 22-30
DOI: 10.31328/jsae.v9i2.7575 ↗Kurz gefasst
Fachartikel in der Zeitschrift JOURNAL OF SCIENCE AND APPLIED ENGINEERING, online erschienen am 26.10.2026. Verfasst von Muhammad Idris und 2 weiteren Autor:innen.
Abstract (Originalsprache)
In the midst of the increasing role of internet services in daily activities, understanding customer perception is key for companies like PT Amarta Lintas Nusantara to maintain service quality. This study aims to implement and evaluate the deep learning model of Long Short-Term Memory (LSTM) to analyze customer sentiment based on text reviews. The data used consisted of 10,000 user reviews collected through the web scraping method, which then went through a series of preprocessing stages such as case folding, tokenization, and lemmatization. The LSTM model was evaluated using three data-sharing scenarios (80:20, 70:30, and 60:40) to find the most optimal configuration. The results showed that the 80:20 ratio provided the best performance with an accuracy of up to 95%. The model shows tremendous strength in classifying Positive sentiment, but has difficulties in the Negative class due to data imbalances. It was concluded that LSTM is a very effective method for this task, and the 80:20 ratio is the most recommended configuration for a balance between training and evaluation.
Zitieren
APA
Idris, M., Nurdiyansyah, F., & Marisa, F. (2026). SENTIMENT ANALYSIS OF PT AMARTA LINTAS NUSANTARA USING THE LONG SHORT-TERM MEMORY (LSTM) METHOD. JOURNAL OF SCIENCE AND APPLIED ENGINEERING, 9(2), 22-30. https://doi.org/10.31328/jsae.v9i2.7575
Vancouver
Idris M, Nurdiyansyah F, Marisa F. SENTIMENT ANALYSIS OF PT AMARTA LINTAS NUSANTARA USING THE LONG SHORT-TERM MEMORY (LSTM) METHOD. JOURNAL OF SCIENCE AND APPLIED ENGINEERING. 2026;9(2):22-30. doi:10.31328/jsae.v9i2.7575
BibTeX
@article{Idris2026,
author = {Idris, Muhammad and Nurdiyansyah, Firman and Marisa, Fitri},
title = {SENTIMENT ANALYSIS OF PT AMARTA LINTAS NUSANTARA USING THE LONG SHORT-TERM MEMORY (LSTM) METHOD},
journal = {JOURNAL OF SCIENCE AND APPLIED ENGINEERING},
year = {2026},
volume = {9},
number = {2},
pages = {22--30},
doi = {10.31328/jsae.v9i2.7575}
}
EUVIMED