Jurnal Teknik Informatika (JUTIF)
Vol. 5 No. 6 (2024): JUTIF Volume 5, Number 6, Desember 2024

COMPARISON OF LOGISTIC REGRESSION AND RANDOM FOREST IN SENTIMENT ANALYSIS OF DISDUKCAPIL APPLICATION REVIEWS

Junianto, Haris (Unknown)
Saputro, Rujianto Eko (Unknown)
Kusuma, Bagus Adhi (Unknown)
Saputra, Dhanar Intan Surya (Unknown)



Article Info

Publish Date
05 Feb 2024

Abstract

Civil registration administration institutions such as Disdukcapil have an important role in carrying out government functions, in supporting the smooth running of administrative services the Government presents the Disdukcapil Mobile Application platform which aims to provide efficient and fast services to the community regarding various population administration needs. Sentiment analysis of user reviews on the Play Store for the Disdukcapil application is needed to understand user perceptions and needs, as well as to improve service quality and application development. In this study, researchers conducted sentiment analysis using 2 algorithms, namely: Logistic Regression and Random Forest, which after comparing by testing the two algorithms with test data of 18810 user review data from PlayStore, obtained the performance results of each algorithm as follows: 90% accuracy, 91% precision, 89% recall, and f1 90% for the performance results of the Logistic Regression algorithm, while for the performance results of the Random Forest algorithm accuracy 89%, precision 92%, recall 86% and f1-score 89%. From these results the Logical Regression algorithm has better performance than the Random Forest algorithm.

Copyrights © 2024






Journal Info

Abbrev

jurnal

Publisher

Subject

Computer Science & IT

Description

Jurnal Teknik Informatika (JUTIF) is an Indonesian national journal, publishes high-quality research papers in the broad field of Informatics, Information Systems and Computer Science, which encompasses software engineering, information system development, computer systems, computer network, ...