Addressing Class Imbalance in Sentiment Analysis of Klik Indomaret Reviews Using SMOTE and Random Forest
DOI:
https://doi.org/10.64479/iarci.v2i1.160Keywords:
sentiment analysis, Klik Indomaret, Google Play Store, Random Forest, SMOTEAbstract
User reviews provide valuable insights into customer satisfaction and application performance. This study analyzes sentiment in Klik Indomaret reviews collected from the Google Play Store using Random Forest and SMOTE to address class imbalance. A total of 3,097 reviews from March 2021 to June 2024 were scraped and labeled into positive and negative sentiment classes based on user ratings. The review texts were preprocessed through case folding, cleaning, tokenization, stopword removal, and stemming, followed by feature extraction using TF-IDF. The dataset was split into training and testing subsets with a 75:25 ratio, and SMOTE was applied to the training data to balance class distribution. The results show that the baseline Random Forest model achieved an accuracy, precision, recall, and F1-score of 0.84, while the RF-SMOTE model improved these metrics to 0.85. These findings indicate that balancing the training data enhances classification performance and reduces bias toward the majority class. The proposed TF-IDF, SMOTE, and Random Forest framework provides an effective approach for sentiment analysis of mobile application reviews and can support service improvement based on user feedback.
Downloads
References
[1] Y. Desnelita, D. Oktarina, J. Nasional, T. Elektro, and dan T. Informasi, “Sentiment Analysis of IKD Application Reviews on Play Store Using Random Forest.” 2025. doi: 10.22146/jnteti.v14i3.20473.
[2] Q. W. Anadia and A. Meiriza, “Performance Comparison of Sentiment Classification Algorithms on SIGNAL Reviews Using SMOTE.” 2025. doi: 10.51519/journalisi.v7i3.1196.
[3] T. Misriati and R. Aryanti, “Optimalisasi Random Forest dan Support Vector Machine dengan Hyperparameter GridSearchCV untuk Analisis Sentimen Ulasan PrimaKu.” 2024. doi: 10.47065/josh.v5i4.5347.
[4] M. Mujahid et al., “Data oversampling and imbalanced datasets: an investigation of performance for machine learning and feature engineering.” 2024. doi: 10.1186/s40537-024-00943-4.
[5] A. Khurana and O. Verma, “Optimal Feature Selection for Imbalanced Text Classification.” 2023. doi: 10.1109/TAI.2022.3144651.
[6] N. Santoso, W. Wibowo, and H. Hikmawati, “Integration of synthetic minority oversampling technique for imbalanced class.” 2019. doi: 10.11591/IJEECS.V13.I1.PP102-108.
[7] M. R. F. Rahmatullah, P. Andono, Affandy, and M. A. Soeleman, “Improving Random Forest Performance for Sentiment Analysis on Unbalanced Data Using SMOTE and BoW Integration: PLN Mobile Application Case Study.” 2025. doi: 10.15294/sji.v12i1.19295.
[8] A. G. Sinaga, R. Robet, and O. Pribadi, “Comprehensive Comparison of TF-IDF and Word2Vec in Product Sentiment Classification Using Machine Learning Models.” 2026. doi: 10.30871/jaic.v10i1.11582.
[9] M. R. Pribadi, D. Manongga, H. Purnomo, I. Setyawan, and Hendry, “Sentiment Analysis of the PeduliLindungi on Google Play using the Random Forest Algorithm with SMOTE.” 2022. doi: 10.1109/ISITIA56226.2022.9855372.
[10] M. R. Syaputa, M. Arifin, and D. L. Fithri, “Klasifikasi Sentimen Ulasan E-Wallet menggunakan TF-IDF dan Random Forest dengan Penyeimbangan Data SMOTE.” 2025. doi: 10.29408/edumatic.v9i2.31084.
[11] M. R. Rahman, A. F. Diansyah, and H. Hanafi, “Sentiment Analysis on the Shopee Application on Playstore Using the Random Forest Classification Method.” 2023. doi: 10.25139/inform.v9i1.5465.
[12] S. A. Memon, M. A. Mahar, A. Kehar, S. Oad, and I. Ahmed, “User Experience Enhancement Through Sentiment Analysis: A Machine Learning Approach to App Reviews.” 2025. doi: 10.58325/ijisct.004.02.00131.
[13] A. Karim, A. Azhari, S. B. Belhaouri, and A. A. Qureshi, “Machine Learning Algorithm’s Measurement and Analytical Visualization of User’s Reviews for Google Play Store.” 2020. doi: 10.20944/preprints202003.0249.v1.
[14] A. Nugroho, Wiyanto, and D. Maulana, “COMPARATIVE ANALYSIS OF CLASSIFICATION ALGORITHMS IN HANDLING IMBALANCED DATA WITH SMOTE OVERSAMPLING APPROACH.” 2025. doi: 10.33480/jitk.v11i2.6956.
[15] M. D. Rizkiyanto, M. D. Purbolaksono, and W. Astuti, “Sentiment Analysis Classification on PLN Mobile Application Reviews using Random Forest Method and TF-IDF Feature Extraction.” 2024. doi: 10.31963/intek.v11i1.4774.
[16] R. Asyrofi and R. Fauzan, “Synthetic-MixUp: A Simple Framework for Imbalanced Text classification.” 2023. doi: 10.1109/GCCE59613.2023.10315313.
[17] U. Kavirayani, K. Mylavarapu, J. Pilli, P. Jannu, J. A. Mohammad, and S. Panchali, “Comparative Performance of Machine Learning Techniques for Sentiment and Insight Analysis in Amazon Product Reviews.” 2022. doi: 10.63282/3117-5481/aijcst-v4i1p106.
[18] S. Pandey, D. Chhabara, A.Vasuki, and S. Indhumathi, “Machine Learning Based Google Play Store Reviews Classification.” 2021. [Online]. Available: https://www.semanticscholar.org/paper/071c7dbb508e36b679dfb6fcb07695da4d4b9e1c
[19] L. S. R and A. P, “Google Playstore Reviews Prediction Using ML And NLP.” [Online]. Available: https://www.semanticscholar.org/paper/8fab6c06f5653d8502f8ba8f0be70964891687ed
[20] Munaldi, “Penerapan Algoritma Random Forest Berbasis TF – IDF untuk Meningkatkan untuk Akurasi Deteksi Sentimen Ulasan Produk E-Commerce.” 2025. doi: 10.30606/rjti.v4i3.4045.
[21] K. P. Harmandini and K. M. L, “Analysis of TF-IDF and TF-RF Feature Extraction on Product Review Sentiment.” 2024. doi: 10.33395/sinkron.v8i2.13376.
[22] H. Barus, I. N. Fajri, and Y. Pristyanto, “Sentiment Classification Analysis of Tokopedia Reviews Using TF-IDF, SMOTE, and Traditional Machine Learning Models.” 2025. doi: 10.30871/jaic.v9i5.10524.
[23] D. S. Assyifa and A. Luthfiarta, “SMOTE-Tomek Re-sampling Based on Random Forest Method to Overcome Unbalanced Data for Multi-class Classification.” 2024. doi: 10.25139/inform.v9i2.8410.
[24] N. Curukoglu and A. Ozpinar, “SMOTE-Text: A Modified SMOTE for Turkish Text Classification.” 2020. doi: 10.1007/978-3-030-79357-9_9.
