The Efektivitas Indobert Dan Bilstm Dengan Fasttext Dalam Analisis Sentimen Ulasan Pengguna Gojek, Grab Dan Maxim
Keywords:
Sentiment Analysis, Indobert, BiLSTM, FastText, Online TransportationAbstract
The growth of online transportation services has increased the number of user reviews on Google Play Store containing sentiment information related to application service quality. This study aims to compare the effectiveness of IndoBERT and the combination of BiLSTM with FastText for sentiment analysis of Gojek, Grab, and Maxim user reviews. The dataset was collected through a scraping process from Google Play Store and processed through preprocessing, tokenization, labeling, model training, and evaluation using accuracy, precision, recall, and F1-score metrics. The results show that IndoBERT achieved the best performance with an accuracy of 0.8961 and an F1-score of 0.8800, while BiLSTM + FastText achieved an accuracy of 0.8518 and an F1-score of 0.8370. These results indicate that IndoBERT is more effective in understanding the context of Indonesian review texts compared to BiLSTM + FastText. However, BiLSTM + FastText has advantages in computational efficiency and lower resource requirements.
References
H. Utama and A. Masruro, "Analisis sentimen pada Twitter menggunakan Word Embedding dengan pendekatan Word2Vec," Jurnal Sistem Cerdas, vol. 5, no. 2, pp. 128–134, 2022, doi: 10.37396/jsc.v5i2.242.
[2] M. I. Wardah and S. D. Putra, "Implementasi machine learning untuk rekomendasi film di IMDb menggunakan collaborative filtering berdasarkan analisa sentimen IMDb," Jurnal Manajamen Informatika Jayakarta, vol. 2, no. 3, pp. 243–249, 2022, doi: 10.52362/jmijayakarta.v2i3.868.
[3] N. A. R. Putri and Ardiansyah, "Analisis sentimen terhadap kemajuan kecerdasan buatan di Indonesia menggunakan BERT dan RoBERTa," Jurnal Sains dan Informatika, vol. 9, no. 2, pp. 136–145, 2023, doi: 10.34128/jsi.v9i2.649.
[4] M. N. Hidayat and R. Pramudita, "Analisis sentimen terhadap pembelajaran secara daring pasca pandemi Covid-19 menggunakan metode IndoBERT," INFORMATION MANAGEMENT FOR EDUCATORS AND PROFESSIONALS: Journal of Information Management, vol. 8, no. 2, pp. 161–170, 2023, doi: 10.51211/imbi.v8i2.2719.
[5] A. Asnawiyah and R. E. Putra, "Perbandingan Algoritma LSTM dan BiLSTM Untuk Analisis Sentimen Multi-Class Media Sosial Twitter," JINACS (Journal of Informatics and Computer Science), vol. 6, no. 3, pp. 778-786, 2024, doi: 10.26740/jinacs.v6n03.p778-786.
[6] J. Asher and E. P. Rachmawati, "Analisis Sentimen Ulasan Bintang Lima Aplikasi Instagram di Google Play Store Menggunakan IndoBERT," DINAMIK, vol. 30, no. 2, pp. 318-329, 2025.
[7] B. R. Ermawan and N. Cahyono, "Optimasi Metode Klasifikasi Menggunakan FastText dan Grid Search pada Analisis Sentimen Ulasan Aplikasi SeaBank," JIKO (Jurnal Informatika dan Komputer), vol. 9, no. 1, pp. 226–238, 2025, doi: 10.26798/jiko.v9i1.1523.
[8] Tarwoto, R. Nugroho, N. Azka, and W. S. R. Graha, "Analisis Sentimen Ulasan Aplikasi Mobile JKN di Google PlayStore Menggunakan IndoBERT," Jurnal JTIK (Jurnal Teknologi Informasi dan Komunikasi), vol. 9, no. 2, pp. 495-505, 2025, doi: 10.35870/jtik.v9i2.3340.
[9] H. F. B. Wewengkang, D. Wungguli, N. I. Yahya, I. K. Hasan, and S. N. Abdussamad, "Implementasi Bidirectional LSTM Dengan Word Embedding FastText Dalam Analisis Sentimen Ulasan Pengguna Aplikasi Maxim," Jurnal Riset Mahasiswa Matematika, vol. 4, no. 5, pp. 204-217, 2025, doi: 10.18860/jrmm/v4i5.33358.
[10] R. Hidayat and W. Gata, "Pemanfaatan IndoBERT dan Long Short-Term Memory (LSTM) pada Analisis Sentimen Ulasan Aplikasi Depok Single Window," Information System for Educators and Professionals, vol. 10, no. 1, pp. 13-24, 2025.
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Fahru Ramdan
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
