Pengukuran Tingkat Akurasi Pada Ulasan E-Commerce Menggunakan Metode INDOBERT Dengan Optimizer Adam

Agung Putra; Ismarmiaty; Apriani

doi:10.53697/jkomitek.v5i1.2448

Authors

Agung Pratama Putra Universitas Bumigora
Ismarmiaty Universitas Bumigora
Apriani Universitas Bumigora

DOI:

https://doi.org/10.53697/jkomitek.v5i1.2448

Keywords:

IndoBERT, Optimizer Adam, E-Commerce, Analisis Sentimen, NLP, Akurasi

Abstract

Pesatnya perkembangan e-commerce di Indonesia telah menyebabkan meningkatnya volume ulasan pengguna, yang kini menjadi sumber informasi penting dalam memahami kepuasan dan pengalaman pelanggan. Ulasan tersebut mengandung sentimen yang dapat dimanfaatkan untuk pengambilan keputusan bisnis, khususnya melalui pendekatan analisis sentimen. Penelitian ini bertujuan untuk mengukur tingkat akurasi model IndoBERT yang dioptimasi menggunakan algoritma Adam dalam mengklasifikasikan sentimen ulasan e-commerce berbahasa Indonesia. Dataset yang digunakan berasal dari platform Kaggle, terdiri atas 11.606 ulasan yang telah melalui tahap pra-pemrosesan seperti pembersihan teks, tokenisasi, dan pelabelan. Data kemudian dibagi menjadi 80% data latih dan 20% data uji. Model yang digunakan merupakan IndoBERT pre-trained yang dioptimasi dengan konfigurasi Adam: learning rate 2e-5, batch size 16, dan 5 epoch pelatihan. Evaluasi model dilakukan dengan menggunakan metrik akurasi, precision, recall, dan F1-score. Hasil evaluasi menunjukkan bahwa model mencapai akurasi sebesar 92,16%, precision 93,16%, recall 91,09%, dan F1-score 92,11%. Confusion matrix juga menunjukkan distribusi prediksi yang seimbang untuk sentimen positif dan negatif. Temuan ini membuktikan bahwa model IndoBERT yang dioptimasi dengan Adam memiliki kinerja yang sangat baik dalam tugas klasifikasi sentimen, serta berpotensi untuk diterapkan dalam sistem analisis sentimen otomatis pada platform e-commerce guna mendukung pengambilan keputusan berbasis data.

References

Anderies. (2021). Finetunning IndoBERT to Understand Indonesian Stock Trader Slang Language. Proceedings of 2021 1st International Conference on Computer Science and Artificial Intelligence, ICCSAI 2021, 42–46. https://doi.org/10.1109/ICCSAI53272.2021.9609746

Baskara, A. R. (2023). Classification of User Reviews for Software Maintenance in Indonesian Language Using IndoBERT-BiLSTM (Case Study: MyPertamina). 2023 8th International Conference on Informatics and Computing, ICIC 2023. https://doi.org/10.1109/ICIC60109.2023.10381946

Computer, J. H. (2023). Sentiment Analysis of Skincare Product Reviews in Indonesian Language using IndoBERT and LSTM. Proceeding - IEEE 9th Information Technology International Seminar, ITIS 2023. https://doi.org/10.1109/ITIS59651.2023.10420222

Darmawan, M. A. (2023). Experiments on IndoBERT Implementation for Detecting Multi-Label Hate Speech with Data Resampling through Synonym Replacement Method. 8th International Conference on Recent Advances and Innovations in Engineering: Empowering Computing, Analytics, and Engineering Through Digital Innovation, ICRAIE 2023. https://doi.org/10.1109/ICRAIE59459.2023.10468099

Euna, S. J. (2020, November 7). BERT: Bidirectional Encoder Representations from Transformer. Sophie Euna Jang. https://sophieeunajang.wordpress.com/2020/11/07/bert/

Garamba, Y., & Nur, A. (2024). Analisis Kepuasan Pelanggan pada E-Commerce. Jurnal Ilmu Komputer dan Informatika| E-ISSN: 3063-9026, 1(2), 27–37.

Febryanti, D. (2024). Customer Sentiment Analysis of Local Skincare Reviews Using IndoBERT and Graph Neural Networks. 2024 International Conference on Intelligent Cybernetics Technology and Applications, ICICyTA 2024, 320–325. https://doi.org/10.1109/ICICYTA64807.2024.10912986

Fernandez, E. (2022). Improving IndoBERT for Sentiment Analysis on Indonesian Stock Trader Slang Language. Proceedings of the 2022 IEEE International Conference on Internet of Things and Intelligence Systems, IoTaIS 2022, 240–244. https://doi.org/10.1109/IoTaIS56727.2022.9975975

Hulliyah, K. (2022). Development of A Chatbot for the Online Application Telegram Chat with An Approach to the Emotion Classification Text Using the Indobert-Lite Method. 2022 4th International Conference on Cybernetics and Intelligent System, ICORIS 2022. https://doi.org/10.1109/ICORIS56080.2022.10031483

Imaduddin, H. (2023). Sentiment Analysis in Indonesian Healthcare Applications using IndoBERT Approach. International Journal of Advanced Computer Science and Applications, 14(8), 113–117. https://doi.org/10.14569/IJACSA.2023.0140813

Kusuma, I. H., & Cahyono, N. (2023). Analisis Sentimen Masyarakat Terhadap Penggunaan E-Commerce Menggunakan Algoritma K-Nearest Neighbor. Jurnal Informatika: Jurnal Pengembangan IT, 8(3), 302–307.

Mei, N. C. (2024). Multi-Label Aspect-Sentiment Classification on Indonesian Cosmetic Product Reviews with IndoBERT Model. International Journal of Advanced Computer Science and Applications, 15(11), 712–720. https://doi.org/10.14569/IJACSA.2024.0151168

Nasution, D. (2024). Strategi Penjualan E-Commerce Untuk Meningkatkan Penjualan Handphone Di Era Digital. Jurnal Teknologi Ilmu Komputer, 3(1), 155–164.

Perwira, R. I. (2025). Domain-Specific Fine-Tuning of IndoBERT for Aspect-Based Sentiment Analysis in Indonesian Travel User-Generated Content. Journal of Information Systems Engineering and Business Intelligence, 11(1), 30–40. https://doi.org/10.20473/jisebi.11.1.30-40

Priambodo, W., & Zuliarso, E. (2024). Combination K-Means And Lstm For Social Media Black Campaign Detection Of Indonesia Presidential Candidates 2024. Jurnal Teknik Informatika (JUTIF), 5(2), 539–550.

Ramdhan, H. M. (2024a). Sentiment Analysis of Beauty Product Reviews Using the IndoBERT Method and Naive Bayes Classification. 2024 12th International Conference on Information and Communication Technology, ICoICT 2024, 397–404. https://doi.org/10.1109/ICoICT61617.2024.10698198

Ramdhan, H. M. (2024b). Sentiment Analysis of Beauty Product Reviews Using the IndoBERT Method and Naive Bayes Classification. 2024 12th International Conference on Information and Communication Technology, ICoICT 2024, 397–404. https://doi.org/10.1109/ICoICT61617.2024.10698198

Sinapoy, M. I. K. (2023). Comparison of LSTM and IndoBERT Method in Identifying Hoax on Twitter. Jurnal RESTI, 7(3), 657–662. https://doi.org/10.29207/resti.v7i3.4830

We Are Social. (2024). Laporan Digital 2024. https://wearesocial-com.translate.goog/id/blog/2024/01/digital-2024/?_x_tr_sl=en&_x_tr_tl=id&_x_tr_hl=id&_x_tr_pto=tc

Yulianti, E. (2024). ABSA of Indonesian customer reviews using IndoBERT: single-sentence and sentence-pair classification approaches. Bulletin of Electrical Engineering and Informatics, 13(5), 3579–3589. https://doi.org/10.11591/eei.v13i5.8032