Sentiment Classification on Indodax Using Term Frequency, FastText, and Neural Attention Models
DOI:
https://doi.org/10.29207/resti.v9i5.6871Keywords:
fasttext embedding, hybrid feature representation, lexicon-based labeling, sentiment analysis, BiLSTM attentionAbstract
The rapid growth of mobile-based investment platforms such as Indodax has triggered a surge in user-generated reviews that reflect public perception and sentiment. This study aimed to develop and evaluate sentiment classification models that can accurately classify Indonesian user reviews on the Indodax app into negative, neutral, and positive sentiments. A dataset of 11,000 reviews was collected via web scraping from the Google Play Store. Reviews were preprocessed, labeled using a lexicon-based unsupervised method, and balanced using oversampling. Two models were built: a Bidirectional LSTM (BiLSTM) with attention mechanism using FastText embeddings, and a Feedforward Neural Network (FFNN) using a hybrid feature vector combining TF-IDF and FastText. The evaluation was performed using accuracy, classification report, confusion matrix, and PCA visualization. The FFNN model outperformed the BiLSTM-Attention model with an accuracy of 97.07% compared to 96.00%. Both models demonstrated strong performance in classifying three sentiment classes, though the FFNN showed better separation in PCA space and higher macro-average metrics. This study demonstrates the effectiveness of combining statistical and semantic feature representations for sentiment classification in Indonesian text. The proposed approach is particularly valuable for low-resource languages and informal user-generated content.
Downloads
References
A. A. Artanti, “Jumlah Investor Kripto Terus Naik di Awal 2024,” metrotvnews.com, 2024. [Online]. Available: https://www.metrotvnews.com/read/NgxCV8qB-jumlah-investor-kripto-terus-naik-di-awal-2024
A. Malik, “OJK Mulai Awasi Kripto – Investor Wajib Tahu Dampaknya,” bareksa.com, 2025. [Online]. Available: https://www.bareksa.com/berita/reksa-dana/2025-02-06/ojk-mulai-awasi-kripto-investor-wajib-tahu-dampaknya?utm_source=chatgpt.com
Muhammad Afif Raihan and Erwin Budi Setiawan, “Aspect Based Sentiment Analysis with FastText Feature Expansion and Support Vector Machine Method on Twitter,” J. RESTI (Rekayasa Sist. dan Teknol. Informasi), vol. 6, no. 4, pp. 591–598, 2022, doi: 10.29207/resti.v6i4.4187.
R. Rahmadani, A. Rahim, and R. Rudiman, “Analisis Sentimen Ulasan ‘Ojol the Game’ Di Google Play Store Menggunakan Algoritma Naive Bayes Dan Model Ekstraksi Fitur Tf-Idf Untuk Meningkatkan Kualitas Game,” J. Inform. dan Tek. Elektro Terap., vol. 12, no. 3, 2024, doi: 10.23960/jitet.v12i3.4988.
B. A. Maulana, M. J. Fahmi, A. M. Imran, and N. Hidayati, “Analisis Sentimen Terhadap Aplikasi Pluang Menggunakan Algoritma Naive Bayes dan Support Vector Machine (SVM),” MALCOM Indones. J. Mach. Learn. Comput. Sci., vol. 4, no. 2, pp. 375–384, 2024, doi: 10.57152/malcom.v4i2.1206.
D. A. Futri, V. E. Irawan, F. Alfaraby, M. A. Fathurrazaq, and G. P. Insany, “Klasifikasi Sentimen Analisis Terhadap Cryptocurrency Exchange Menggunakan Naive Bayes Untuk Mendukung Keputusan Investor Pemula,” Sentim. (Seminar Nas. Teknol. Informasi, Mekatornika dan Ilmu Komputer), 2024.
A. Syahrul, A. I. Purnamasari, and I. Ali, “Analisis Sentimen Twitter Terhadap Cryptocurrency Menggunakan Algoritma Naive Bayes dan Decision Tree,” JATI (Jurnal Mhs. Tek. Inform., vol. 8, no. 2, pp. 1–8, 2024.
Verra Budhi Lestari, Ema Utami, and Hanafi, “Combining Bi-LSTM And Word2vec Embedding For Sentiment Analysis Models Of Application User Reviews,” Indones. J. Comput. Sci., vol. 13, no. 1, pp. 312–326, 2024, doi: 10.33022/ijcs.v13i1.3647.
M. A. S. Nasution and E. B. Setiawan, “Enhancing Cyberbullying Detection on Indonesian Twitter: Leveraging FastText for Feature Expansion and Hybrid Approach Applying CNN and BiLSTM,” Rev. d’Intelligence Artif., vol. 37, no. 4, pp. 929–936, 2023, doi: 10.18280/ria.370413.
L. Saragih, M. Nababan, Y. Simatupang, and J. Amalia, “Analisis Self-Attention Pada Bi-Directional Lstm Dengan Fasttext Dalam Mendeteksi Emosi Berdasarkan Text,” Zo. J. Sist. Inf., vol. 4, no. 2, pp. 144–156, 2022, doi: 10.31849/zn.v4i2.10846.
C. Hayati, S. S. Hilabi, A. L. Hananto, S. Informasi, U. Buana, and P. Karawang, “Klasifikasi dan Prediksi Ulasan Apliaksi Dana pada Google PlayStore Menggunakan Algoritma Naive Bayes,” JINTEKS (Jurnal Inform. dan Sains), vol. 7, no. 2, pp. 596–605, 2025.
A. Fauzul, A. Kustiwa, M. Aminul Akbar, and A. Pinandito, “Studi Perbandingan pada Metode CNN-LSTM dan LSTM dalam Mendeteksi Emosi pada Data Teks Berbahasa Indonesia pada Media Sosial Twitter,” J. Pengemb. Teknol. Inf. dan Ilmu Komput., vol. 1, no. 1, pp. 2548–964, 2017, [Online]. Available: http://j-ptiik.ub.ac.id
M. Chiny, M. Chihab, Y. Chihab, and O. Bencharef, “LSTM, VADER and TF-IDF based Hybrid Sentiment Analysis Model,” Int. J. Adv. Comput. Sci. Appl., vol. 12, no. 7, pp. 265–275, 2021, doi: 10.14569/IJACSA.2021.0120730.
Alfando and R. Hayami, “Klasifikasi Teks Berita Berbahasa Indonesia Menggunakan Machine Learning dan Deep Learning: Studi Literatur,” JATI (Jurnal Mhs. Tek. Inform., vol. 7, no. 1, pp. 681–686, 2023.
google, “Indodax Kripto Mudah Aman Cuan,” play.google.com. Accessed: Jun. 29, 2025. [Online]. Available: https://play.google.com/store/apps/details?id=id.co.bitcoin&hl=id
N. Nurwanda, N. Suarna, and W. Prihartono, “Penerapan Nlp (Natural Language Processing) Dalam Analisis Sentimen Pengguna Telegram Di Playstore,” JATI (Jurnal Mhs. Tek. Inform., vol. 8, no. 2, pp. 1841–1846, 2024, doi: 10.36040/jati.v8i2.8469.
D. Normawati and S. A. Prayogi, “Implementasi Naïve Bayes Classifier Dan Confusion Matrix Pada Analisis Sentimen Berbasis Teks Pada Twitter,” J. Sains Komput. Inform. (J-SAKTI, vol. 5, no. 2, pp. 697–711, 2021.
K. Machová, M. Mikula, X. Gao, and M. Mach, “Lexicon-based sentiment analysis using particle swarm optimization,” Electron., vol. 9, no. 8, pp. 1–22, 2020, doi: 10.3390/electronics9081317.
G. Li, B. Li, L. Huang, and S. Hou, “Automatic construction of a depression-domain lexicon based on microblogs: Text mining study,” JMIR Med. Informatics, vol. 8, no. 6, pp. 1–17, 2020, doi: 10.2196/17650.
H. Utama, E. Daniati, and A. Masruro, “Weak Supervision Dengan Pendekatan Labeling Function Untuk Analisis Sentimen Pada Twitter,” Indones. J. Comput. Sci. Res., vol. 3, no. 1, pp. 49–57, 2024, doi: 10.59095/ijcsr.v3i1.93.
T. Wongvorachan, S. He, and O. Bulut, “A Comparison of Undersampling, Oversampling, and SMOTE Methods for Dealing with Imbalanced Classification in Educational Data Mining,” Inf., vol. 14, no. 1, 2023, doi: 10.3390/info14010054.
S. Wang, Y. Dai, J. Shen, and J. Xuan, “Research on expansion and classification of imbalanced data based on SMOTE algorithm,” Sci. Rep., vol. 11, no. 1, pp. 1–11, 2021, doi: 10.1038/s41598-021-03430-5.
K. Babić, S. Martinčić-Ipšić, and A. Meštrović, “Survey of neural text representation models,” Inf., vol. 11, no. 11, pp. 1–32, 2020, doi: 10.3390/info11110511.
J. Philip Thekkekara, S. Yongchareon, and V. Liesaputra, “An attention-based CNN-BiLSTM model for depression detection on social media text,” Expert Syst. Appl., vol. 249, no. PC, p. 123834, 2024, doi: 10.1016/j.eswa.2024.123834.
A. Borah, M. P. Barman, and A. Awekar, Are Word Embedding Methods Stable and Should We Care about It?, vol. 1, no. 1. Association for Computing Machinery, 2021. doi: 10.1145/3465336.3475098.
A. Mohammadi and A. Shaverizade, “Ensemble deep learning for aspect-based sentiment analysis,” Int. J. Nonlinear Anal. Appl., vol. 12, no. Special Issue, pp. 29–38, 2021, doi: 10.22075/IJNAA.2021.4769.
Ž. Vujović, “Classification Model Evaluation Metrics,” Int. J. Adv. Comput. Sci. Appl., vol. 12, no. 6, pp. 599–606, 2021, doi: 10.14569/IJACSA.2021.0120670.
Downloads
Published
Issue
Section
License
Copyright in each article belongs to the author
- The author acknowledges that the RESTI Journal (System Engineering and Information Technology) is the first publisher to publish with a license Creative Commons Attribution 4.0 International License.
- Authors can enter writing separately, arrange the non-exclusive distribution of manuscripts that have been published in this journal into other versions (eg sent to the author's institutional repository, publication in a book, etc.), by acknowledging that the manuscript has been published for the first time in the RESTI (Rekayasa Sistem dan Teknologi Informasi) journal ;





