Perbandingan analisis sentimen PLN Mobile: Machine learning vs. deep learning

Akbar, Ismail and Faisal, Muhammad ORCID: https://orcid.org/0000-0003-4884-7254 (2024) Perbandingan analisis sentimen PLN Mobile: Machine learning vs. deep learning. JOINTECS (Journal of Information Technology and Computer Science), 8 (1). pp. 1-10. ISSN 25416448

Text 19172.pdf - Published Version Available under License Creative Commons Attribution Share Alike. Download (580kB)

Abstract

Play Store app ratings hold significant value as they offer critical insights for app developers to enhance digital service quality. The research centers on the PLN Mobile app, which has garnered mixed user opinions since its launch. These reviews come with challenges for users and developers when interpreting user comments. This study conducts tests,comparing several machine learning algorithms: logistic regression, decision trees, random forests, and specific deep learning algorithms, including neural network multi-layer perceptron (MLP) and long short-term memory (LSTM) for sentiment classification, i.e., positive or negative. The study collected 3,000 PLN Mobile user reviews, comprising 1,965 positive and 1,035 negative reviews. Logistic regression achieved an 84.47% accuracy rate, decision trees scored 79.30%, and random forests reached 83.64%. In contrast, deep learning models, particularly the Neural Network Multilayer Perceptron (MLP), reached an accuracy rate of 84.47%, while the LSTM achieved an accuracy rate of 78.83%. In the context of sentiment analysis of PLN Mobile user reviews, machine learning models using the logistic regression algorithm and deep learning models employing the multi-layer perceptron (MLP) neural network algorithm demonstrated higher accuracy compared to other methods.

Item Type:	Journal Article
Keywords:	sentiment analysis; machine learning; deep learning; PLN Mobile
Subjects:	08 INFORMATION AND COMPUTING SCIENCES > 0801 Artificial Intelligence and Image Processing > 080107 Natural Language Processing
Divisions:	Faculty of Technology > Department of Informatics Engineering
Depositing User:	Muhammad Faisal
Date Deposited:	03 Jun 2024 21:57

Downloads

Origin of downloads

Actions (login required)

View Item