Article Per Year (5 Year)
p-Index From 2021 - 2026
0.408
P-Index
This Author published in this journals
All Journal Jurnal Teknologi Informasi MURA Jurnal Teknologi Informasi Mura
Resti Julia Amayani Yenni
Unknown Affiliation
Computer Science & IT Control & Systems Engineering Decision Sciences, Operations Research & Management Other

Published : 2 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 2 Documents
Search

 1 
EVALUASI KINERJA DECISION TREE DAN LOGISTIC REGRESSION PADA ANALISIS SENTIMEN ULASAN GOJEK Resti Julia Amayani Yenni; Dodo Zeinal Abidin; Jasmir
Jurnal Teknologi Informasi Mura Vol. 18 No. 2 (2026): Jurnal Teknologi Informasi Mura JUNI
Publisher : LPPM UNIVERSITAS BINA INSAN

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32767/jti.v18i2.3292

Abstract

Sentiment analysis of Gojek reviews has been widely conducted; however, comparisons of Decision Tree and Logistic Regression with class imbalance handling using SMOTE and ADASYN remain limited. This study aims to compare the performance of both algorithms under baseline, SMOTE, and ADASYN scenarios using 225,002 Gojek reviews represented by TF-IDF. Hyperparameter tuning was performed using Grid Search and 5-Fold Cross Validation, while differences between models were evaluated using the McNemar test. The novelty of this study lies in the comparative evaluation of six configurations, consisting of two classification algorithms across three class imbalance handling scenarios, systematically analyzed through hyperparameter tuning, 5-Fold Cross Validation, and the McNemar test. The results show that Logistic Regression with SMOTE achieved the highest cross-validation F1-score of 0.8946, while Decision Tree achieved its highest score of 0.8100 under the baseline scenario. These findings indicate that the effectiveness of oversampling depends on the algorithm used. This study contributes empirical evidence for selecting sentiment classification strategies and supports the automation of user review evaluation.
EVALUASI KINERJA DECISION TREE DAN LOGISTIC REGRESSION PADA ANALISIS SENTIMEN ULASAN GOJEK Resti Julia Amayani Yenni; Dodo Zeinal Abidin; Jasmir
Jurnal Teknologi Informasi Mura Vol. 18 No. 2 (2026): Jurnal Teknologi Informasi Mura JUNI
Publisher : LPPM UNIVERSITAS BINA INSAN

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32767/jti.v18i2.3292

Abstract

Sentiment analysis of Gojek reviews has been widely conducted; however, comparisons of Decision Tree and Logistic Regression with class imbalance handling using SMOTE and ADASYN remain limited. This study aims to compare the performance of both algorithms under baseline, SMOTE, and ADASYN scenarios using 225,002 Gojek reviews represented by TF-IDF. Hyperparameter tuning was performed using Grid Search and 5-Fold Cross Validation, while differences between models were evaluated using the McNemar test. The novelty of this study lies in the comparative evaluation of six configurations, consisting of two classification algorithms across three class imbalance handling scenarios, systematically analyzed through hyperparameter tuning, 5-Fold Cross Validation, and the McNemar test. The results show that Logistic Regression with SMOTE achieved the highest cross-validation F1-score of 0.8946, while Decision Tree achieved its highest score of 0.8100 under the baseline scenario. These findings indicate that the effectiveness of oversampling depends on the algorithm used. This study contributes empirical evidence for selecting sentiment classification strategies and supports the automation of user review evaluation.
Co-Authors Dodo Zeinal Abidin Jasmir