Sentiment Analysis of User Reviews on Maxim Application Using the Long Short-Term Memory (LSTM) Methods

Maria Ilona Junide Bria; Anik Vega Vitianingsih; Anastasia Lidya Maukar; SY.  Yuliani; Pamudi Pamudi

doi:10.51454/decode.v5i3.1257

Authors

Maria Ilona Junide Bria Informatic Engineering Universitas Dr. Soetomo
Anik Vega Vitianingsih Informatic Engineering Universitas Dr. Soetomo
Anastasia Lidya Maukar Industrial Engineering Universitas Presiden
SY. Yuliani Informatic Universitas Multimedia Nusantara Jakarta
Pamudi Pamudi Informatic Engineering Universitas Dr. Soetomo

DOI:

https://doi.org/10.51454/decode.v5i3.1257

Keywords:

Machine Learning, Maxim Apps, Natural Language Processing, Sentiment Analysis, Service Quality

Abstract

The technological developments have encouraged the emergence of app-based transportation services that are increasingly popular with the public, one of which is the Maxim app. Despite offering convenience in booking transportation and other services, this app still receives various reviews from users regarding service quality. User feedback is provided through the Maxim app review section available on the Google Play Store platform. Sentiment analysis is applied in this study to identify shortcomings in the Maxim app, to help developers improve service quality and understand user satisfaction. The research procedure it comprises several phases, including data collection, text preprocessing, determining sentiment labels, assigning weights to terms, and a classification process using the Long Short-Term Memory (LSTM) algorithm. This studi unlike previous studies that commonly used classical machine learning techniques including Naïve Bayes and SVM, or BiLSTM, this research applies an LSTM model with lexicon-based sentiment labeling to improve consistency and contextual understanding in sentiment classification. A confusion matrix was utilized to evaluate the model’s performance. Overall, 1,200 user reviews were gathered through web scraping techniques from June 2024 to June 2025. The sentiment classification process uses a lexicon-based method to categorize user reviews grouped into three sentiment classes: positive, neutral, and negative. The findings suggest that 762 reviews are labelled as positive, 157 as neutral, and 281 as negative. The LSTM method testing demonstrated excellent performance, achieved 95.21% accuracy, 97.22% precision, 84.02% recall, and an F1-score of 88.84%.

References

Alghifari, D. R., Edi, M., & Firmansyah, L. (2022). Implementasi Bidirectional Lstm Untuk Analisis Sentimen Terhadap Layanan Grab Indonesia. Jurnal Manajemen Informatika (Jamika), 12(2), 89–99. https://doi.org/10.34010/jamika.v12i2.7764

Aripiyanto, S., Tukino, T., Sufyan, A., & Nandaputra, R. (2022). Sentimen Analisis Twitter Ibu Kota Negara Nusantara Menggunakan Long Short-Term Memory Dan Lexicon Based. Expert: Jurnal Manajemen Sistem Informasi Dan Teknologi, 12(2), 119-125. https://dx.doi.org/10.36448/expert.v12i2.2821

Aulia, T. M. P., Arifin, N., & Mayasari, R. (2021). Perbandingan Kernel Support Vector Machine (Svm) Dalam Penerapan Analisis Sentimen Vaksinisasi Covid-19. Sintech (Science And Information Technology) Journal, 4(2), 139–145. https://doi.org/10.31598/sintechjournal.v4i2.762

Damayanti, E., Vitianingsih, A. V., Kacung, S., Suhartoyo, H., & Lidya Maukar, A. (2024). Sentiment Analysis Of Alfagift Application User Reviews Using Long Short-Term Memory (Lstm) And Support Vector Machine (Svm) Methods. Decode: Jurnal Pendidikan Teknologi Informasi, 4(2), 509–521. https://doi.org/10.51454/decode.v4i2.478

Dipietro, R., & Hager, G. D. (2020). Deep Learning: Rnns And Lstm. In Handbook Of Medical Image Computing And Computer Assisted Intervention, 503–519. https://doi.org/10.1016/B978-0-12-816176-0.00026-0

Gaafar, A. S., Dahr, J. M., & Hamoud, A. K. (2022). Comparative Analysis Of Performance Of Deep Learning Classification Approach Based On Lstm-Rnn For Textual And Image Datasets. Informatica (Slovenia), 46(5), 21–28. https://doi.org/10.31449/inf.v46i5.3872

Hakim, B. (2021). Analisa Sentimen Data Text Preprocessing Pada Data Mining Dengan Menggunakan Machine Learning. Jbase - Journal Of Business And Audit Information Systems, 4(2), 16-22. http://dx.doi.org/10.30813/jbase.v4i2.3000

Hasanah, A. N., & Sari, B. N. (2024). Analisis Sentimen Ulasan Pengguna Aplikasi Jasa Ojek Online Maxim Pada Google Play Dengan Metode Naive Bayes Classifier. Jurnal Informatika Dan Teknik Elektro Terapan, 12(1), 60-96. https://doi.org/10.23960/jitet.v12i1.3628

Husein, A. M., Muntaza, L. H., Sinaga, G., Khoirulliza, K., & Sembiring, M. L. B. (2025). Model Cnn-Lstm Untuk Klasifikasi Tingkat Stres Mahasiswa Dalam Menghadapi Ujian Menggunakan Data Elektrokardiogram (Ekg). Decode: Jurnal Pendidikan Teknologi Informasi, 5(1), 191–201. https://doi.org/10.51454/decode.v5i1.1080

Iqrom, M., Afdal, M., Novita, R., Rahmawita, M., & Ahsyar, T. K. (2025). Sentiment Analysis Of Gojek, Grab, And Maxim Applications Using Support Vector Machine Algorithm. Jurnal Inovtek Polbeng - Seri Iformatika, 10(1), 237-248. https://doi.org/10.35314/52fycr56

Kokab, S. T., Asghar, S., & Naz, S. (2022). Transformer-Based Deep Learning Models For The Sentiment Analysis Of Social Media Data. Computers & Operations Research, 14, 100157. https://doi.org/10.1016/j.array.2022.100157

Labuguen, M. Z. (2025). Enhancing Lstm Performance In Sentiment Analysis Through Advanced Data Preprocessing And Model Optimization Techniques. World Journal Of Advanced Research And Reviews, 25(1), 2433–2443. https://doi.org/10.30574/wjarr.2025.25.1.0098

Mandar, G., Muhamamd, A. H., & Sudin, S. (2020). Klasifikasi Berita Indonesia Menggunakan Naïve Bayes Dengan Porter Stemmer. Jurnal Teknik Informatika (J-Tifa), 3(2), 17–22. https://doi.org/10.52046/j-tifa.v3i2.1121

Otter, D. W., Medina, J. R., & Kalita, J. K. (2021). A Survey Of The Usages Of Deep Learning For Natural Language Processing. Ieee Transactions On Neural Networks And Learning Systems, 32(2), 604–624. https://doi.org/10.1109/TNNLS.2020.2979670

Pohan, S. A., Samsudin, S., & Sibarani, F. H. (2024). Analisis Sentimen Terhadap Aplikasi Maxim Menggunakan Algoritma Random Forest. Journal Of Science And Social Research, 7(3), 1201–1208.

Putri, N. A., Srirahayu, A., & Arif Sudibyo, N. (2025). Analisis Sentimen Terhadap Aplikasi Kitalulus Menggunakan Metode Naive Bayes Dari Ulasan Google Play Store. Smart Comp: Jurnalnya Orang Pintar Komputer, 14(2), 269-279. https://doi.org/10.30591/smartcomp.v14i2.7230

Putri, N. K., Vitianingsih, A. V., Kacung, S., Maukar, A. L., & Yasin, V. (2024). Sentiment Analysis Of Brand Ambassador Influence On Product Buyer Interest Using Knn And Svm. Indonesian Journal Of Artificial Intelligence And Data Mining, 7(2), 327 – 336 http://dx.doi.org/10.24014/ijaidm.v7i2.29469

Rizki, M. R., & Sanjaya, M. R. (2024). Maxim Application User Satisfaction Analysis Using The User Experience Questionnaire Method. INOVTEK Polbeng - Seri Informatika, 9(2), 814–825. https://doi.org/10.35314/3p1r9s88

Saputra, A., Hariyono, R. C. S., & Saraswati, N. M. (2024). Analisis Sentimen Pengguna Aplikasi Mypertamina Menggunakan Algoritma Bidirectional Long Short Term Memory. Jurnal Eksplora Informatika, 13(2), 156–163. https://doi.org/10.30864/eksplora.v13i2.973

Saputra, M., & Wahyuni, S. (2024). Analisis Sentimen Pengguna Pada Aplikasi Bank Digital Krom Dengan Algoritma Support Vector Machine. Infotech Journal, 10(2), 327–332. https://doi.org/10.31949/infotech.v10i2.11801

Selle, N., Yudistira, N., & Dewi, C. (2022). Perbandingan Prediksi Penggunaan Listrik Denganmetode Long Short-Term Memory (Lstm) Dan Recurrent Neural Network (RNN). Jurnal Teknologi Informasi Dan Ilmu Komputer, 9(1), 155–162. https://doi.org/10.25126/jtiik.2022915585

Shyahrin, M. V., Sibaroni, Y., & Puspandari, D. (2023). Penerapan Metode Long Short-Term Memory Dan Word2vec Dalam Analisis Sentimen Ulasan Pada Aplikasi Ferizy Lstm And Word2vec Application For Sentiment Analysis Of Reviews On Ferizy. Academic Journal, 22(4), 833–842. https://doi.org/10.33633/tc.v22i4.9205

Sujadi, H. (2022). Analisis Sentimen Pengguna Media Sosial Twitter Terhadap Wabah Covid-19 Dengan Metode Naive Bayes Classifier Dan Support Vector Machine. Infotech Journal, 8(1), 22–27. https://doi.org/10.31949/infotech.v8i1.1883

Tamami, G., Triyanto, W. A., & Muzid, S. (2025). Sentiment Analysis Mobile Jkn Reviews Using Smote Based Lstm. Ijccs (Indonesian Journal Of Computing And Cybernetics Systems), 19(1), 13-24. https://doi.org/10.22146/ijccs.101910

Valero-Carreras, D., Alcaraz, J., & Landete, M. (2023). Comparing Two Svm Models Through Different Metrics Based On The Confusion Matrix. Computers & Operations Research, 152, 106131. https://doi.org/10.1016/j.cor.2022.106131

Wewengkang, H. F. B., Wungguli, D., Yahya, N. I., Hasan, I. K., & Abdussamad, S. N. (2025). Implementasi Bidirectional Lstm Dengan Word Embedding Fasttext Dalam Analisis Sentimen Ulasan Pengguna Aplikasi Maxim. Riset Mahasiswa Matematika, 4(5), 204–217. https://doi.org/10.18860/jrmm.v4i5.33358

Widyaningrum, I., & Kamayani, M. (2023). Analisis Sentimen Opini Masyarakat Terhadap Penggunaan Layanan Maxim Menggunakan Algoritma Naïve Bayes. Jurnal Coscitech (Computer Science And Information Technology), 4(3), 651–660. https://doi.org/10.37859/coscitech.v4i3.6194

Wirayani, N. A., Wirastuti, N. M. A. E. D., & Manuaba, I. B. G. (2025). Analisis Sentimen Tanggapan Masyarakat Tentang Garuda Ikn Menggunakan Metode Naive Bayes. Decode: Jurnal Pendidikan Teknologi Informasi, 5(1), 27–40. Https://Doi.Org/10.51454/Decode.V5i1.860