Implementasi Bidirectional Encoder Representations from Transformers (BERT) untuk Analisis Sentimen Ulasan Aplikasi Ibis Paint X

Esti Setiyaningsih; Ety Sutanty; Maukar

doi:10.51454/decode.v5i3.1413

Authors

Esti Setiyaningsih Informatika Universitas Gunadarma
Ety Sutanty Sistem Informasi Universitas Gunadarma
Maukar Magister Manajemen Sistem Informasi Universitas Gunadarma

DOI:

https://doi.org/10.51454/decode.v5i3.1413

Keywords:

Analisis Sentimen, BERT, Ibis Paint X, Pelabelan, Transformers

Abstract

Perkembangan aplikasi seni digital memunculkan banyak ulasan pengguna yang bermanfaat bagi pengembang, namun sulit dievaluasi secara manual. Penelitian ini menganalisis sentimen 8.500 ulasan berbahasa Indonesia pada aplikasi Ibis Paint X yang diperoleh melalui proses scraping Google Play Store menggunakan google-play-scraper. Dataset terdiri atas dua kolom utama, yaitu review_text dan category (rating), kemudian melalui tahap preprocessing mencakup pelabelan, pembersihan teks, penghapusan stopwords, tokenisasi, serta normalisasi. Setelah dibagi menjadi data latih (70%), validasi (15%), dan uji (15%), model IndoBERT di-fine-tuning selama lima epoch untuk melakukan klasifikasi sentimen positif, negatif, dan netral. Evaluasi performa model dilakukan menggunakan akurasi, precision, recall, F1-score, serta confusion matrix. Hasil pengujian menunjukkan akurasi sebesar 87%. Kinerja model paling tinggi pada kelas sentimen negatif dengan precision 0,94, recall 0,96, dan F1-score 0,95. Namun, performa pada kelas positif (F1-score 0,52) dan netral (F1-score 0,31) masih rendah, sebagaimana turut tercermin pada confusion matrix yang menunjukkan banyaknya kesalahan klasifikasi menuju kelas positif yang dominan. Temuan ini menegaskan efektivitas BERT dalam analisis sentimen berbahasa Indonesia, sekaligus menunjukkan perlunya penanganan ketidakseimbangan data untuk meningkatkan performa pada seluruh kategori sentimen.

References

Alaparthi, S., & Mishra, M. (2020). Bidirectional Encoder Representations from Transformers (BERT): A sentiment analysis odyssey. 1, 1-20. https://doi.org/10.48550/arXiv.2007.01127

Albab, M. U., P., Y. K., & Fawaiq, M. N. (2023). Optimization of the Stemming Technique on Text Preprocessing President 3 Periods Topic. Jurnal Transformatika, 20(2), 1–12. https://doi.org/10.26623/transformatika.v20i2.5374

Aliero, A. A., Adebayo, B. S., Aliyu, H. O., Tafida, A. G., Kangiwa, B. U., & Dankolo, N. M. (2023). Systematic Review on Text Normalization Techniques and its Approach to Non-Standard Words. International Journal of Computer Applications, 185(33), 44–55. https://doi.org/10.5120/ijca2023923106

Areshey, A., & Mathkour, H. (2023). Transfer Learning For Sentiment Classification Using Bidirectional Encoder Representations From Transformers (BERT) Model. Sensors, 23(11). https://doi.org/10.3390/s23115232

Cahyawijaya, S., Winata, G. I., Wilie, B., Vincentio, K., Li, X., Kuncoro, A., Ruder, S., Lim, Z. Y., Bahar, S., Khodra, M. L., Purwarianti, A., & Fung, P. (2021). IndoNLG: Benchmark and Resources for Evaluating Indonesian Natural Language Generation. EMNLP 2021 - 2021 Conference on Empirical Methods in Natural Language Processing, Proceedings, 8875–8898. https://doi.org/10.18653/v1/2021.emnlp-main.699

Diaz, G. (2025). Stopwords-id. https://github.com/stopwords-iso/stopwords-id

Hadiprakoso, R. B., Setiawan, H., Yasa, R. N., & Girinoto. (2023). Text Preprocessing for Optimal Accuracy in Indonesian Sentiment Analysis Using a Deep Learning Model with Word Embedding. AIP Conference Proceedings, 2680(1). https://doi.org/10.1063/5.0126116

Hasanudin, C., Mayasari, N., Saddhono, K., & Prabowo, R. A. (2021). IbisPaint X Apps in Creating Collaborative 3D Learning media of Pop-Up and Movable Books. Journal of Physics: Conference Series, 1764(1). https://doi.org/10.1088/1742-6596/1764/1/012131

Jupin-Delevaux, É., Djahnine, A., Talbot, F., Richard, A., Gouttard, S., Mansuy, A., Douek, P., Si-Mohamed, S., & Boussel, L. (2023). BERT-Based Natural Language Processing Analysis Of French CT Reports: Application To The Measurement Of The Positivity Rate For Pulmonary Embolism. Research in Diagnostic and Interventional Imaging, 6, 100027. https://doi.org/10.1016/j.redii.2023.100027

Latif, R. M. A., Abdullah, M. T., Shah, S. U. A., Farhan, M., Ijaz, F., & Karim, A. (2019). Data Scraping From Google Play Store And Visualization Of Its Content For Analytics. 2019 2nd International Conference on Computing, Mathematics and Engineering Technologies, ICoMET 2019, July 2020. https://doi.org/10.1109/ICOMET.2019.8673523

Li, H., Xue, T., Zhang, A., Luo, X., Kong, L., & Huang, G. (2024). The Application And Impact Of Artificial Intelligence Technology In Graphic Design: A Critical Interpretive Synthesis. Heliyon, 10(21), e40037. https://doi.org/10.1016/j.heliyon.2024.e40037

Maulana, A., Rozikin, C., & Surharso, A. (2025). Sentiment Analysis Of Indonesia National Team Naturalization Using Bidirectional Encoder Representations From Transformers. Informatika Dan Sains, 15(01), 2025. https://doi.org/10.54209/infosains.v15i01

Mustak, M., Hallikainen, H., Laukkanen, T., Plé, L., Hollebeek, L. D., & Aleem, M. (2024). Using Machine Learning To Develop Customer Insights From User-Generated Content. Journal of Retailing and Consumer Services, 81(July). https://doi.org/10.1016/j.jretconser.2024.104034

Nawawi, I., Ilmawan, K. F., Maarif, M. R., & Syafrudin, M. (2024). Exploring Tourist Experience through Online Reviews Using Aspect-Based Sentiment Analysis with Zero-Shot Learning for Hospitality Service Enhancement. Information (Switzerland), 15(8). https://doi.org/10.3390/info15080499

Oliaee, A. H., Das, S., Liu, J., & Rahman, M. A. (2023). Using Bidirectional Encoder Representations From Transformers (BERT) To Classify Traffic Crash Severity Types. Natural Language Processing Journal, 3, 100007. https://doi.org/10.1016/j.nlp.2023.100007

Pradipta, D., & Widodo, E. (2024). Sentiment Analysis on Social Media using Bidirectional Encoder from Transformers (Case Study : Covid – 19 Omicron). INFORMASI (Jurnal Informatika Dan Sistem Informasi), 16(2), 267–281. https://doi.org/10.37424/informasi.v16i2.319

Rayhan, R., Rayhan, A., & Kinzler, R. (2023). Exploring the Power of Data Manipulation and Analysis: A Comprehensive Study of NumPy, SciPy, and Pandas. ResearchGate, 1-23. https://doi.org/10.13140/RG.2.2.22390.16968

Wang, J., & Zhang, J. (2024). Research on the Theory and Innovation Strategy of Digital Media Art Development Based on Artificial Intelligence Technology. Applied Mathematics and Nonlinear Sciences, 9(1), 1-20. https://doi.org/10.2478/amns-2024-1543