Pengembangan Model Fine-Tuning IndoBERT Untuk Deteksi Topik dan Analisis Sentimen Ulasan Produk Berbasis Aspek
Article Sidebar
Main Article Content
Abstract
Pertumbuhan e-commerce di Indonesia menghasilkan lonjakan data ulasan produk yang menjadi referensi utama bagi konsumen sebelum melakukan pembelian. Namun, membaca ulasan secara manual sangatlah tidak efisien, ditambah dengan adanya tantangan berupa ulasan palsu (fake review) dan ketidakseimbangan opini (class imbalance). Oleh karena itu, penelitian ini bertujuan mengembangkan sebuah browser extension terintegrasi Dashboard Analitik yang mampu merangkum ulasan secara otomatis dan real-time langsung pada halaman produk. Sistem ini dibangun menggunakan pendekatan Hybrid Aspect-Based Sentiment Analysis (ABSA) yang memadukan ekstraksi kamus leksikon (Rule-Based) untuk 7 kategori aspek (Pengiriman, Harga, Kualitas Produk, Kemasan, Pelayanan, Kesesuaian Produk, dan Umum) dengan model Deep Learning IndoBERT untuk klasifikasi sentimen biner (Positif dan Negatif). Guna menangani ketidakseimbangan data, dataset gabungan sebanyak 488.556 ulasan mentah diproses dan diseimbangkan menggunakan teknik undersampling hingga menghasilkan 260.430 sampel latih yang ideal. Ekstensi ini juga dilengkapi dengan algoritma heuristik pada sisi klien (client-side) untuk mendeteksi indikasi fake review. Hasil pengujian Blackbox membuktikan bahwa seluruh fungsionalitas sistem—seperti ekstraksi batch, injeksi badge sentimen pada elemen web (DOM), dan fitur ekspor data—berjalan dengan tingkat keberhasilan 100%. Selain itu, pengujian penerimaan pengguna menggunakan metode System Usability Scale (SUS) terhadap 36 responden memperoleh skor 64,10 (Marginal High / Good). Kesimpulan dari penelitian ini menunjukkan bahwa integrasi IndoBERT ke dalam browser extension terbukti andal dan fungsional dalam membantu konsumen menyaring dan memahami nilai jual suatu produk secara komprehensif.
Downloads
Article Details
Section
This work is licensed under a Creative Commons Attribution 4.0 International License.
References
[1] N. Malik and M. Bilal, “Natural language processing for analyzing online customer reviews: a survey, taxonomy, and open research challenges,” PeerJ Comput. Sci., vol. 10, 2024, doi: 10.7717/PEERJ-CS.2203.
[2] K. Bhadauria Student and B. Vidyapith, “Customer Sentiment Analysis Based on App Reviews for the Automotive Industry,” 2023. [Online]. Available: http://www.ijritcc.org
[3] H. Imaduddin, F. Yusfida A’la, and Y. S. Nugroho, “Sentiment Analysis in Indonesian Healthcare Applications using IndoBERT Approach,” 2023. [Online]. Available: www.ijacsa.thesai.org
[4] R. Labib Mustofa, C. Edi Widodo, and P. Korespondensi, “Aspect-Based Sentiment Analysis On The Central Java Public Satisfaction Survey Electronic Application (E-SKM) Using IndoBERT,” Jurnal Teknologi Informaasi dan Ilmu Komputer, vol. 12, no. 4, pp. 867–874, 2025.
[5] L. Geni, E. Yulianti, and D. I. Sensuse, “Sentiment Analysis of Tweets Before the 2024 Elections in Indonesia Using Bert Language Models,” Jurnal Ilmiah Teknik Elektro Komputer dan Informatika, vol. 9, no. 3, pp. 746–757, Aug. 2023, doi: 10.26555/jiteki.v9i3.26490.
[6] F. Ayu, D. Aryanti, A. Luthfiarta, D. Adiwinata, and I. Soeroso, “Aspect-Based Sentiment Analysis with LDA and IndoBERT Algorithm on Mental Health App: Riliv,” 2025. [Online]. Available: http://jurnal.polibatam.ac.id/index.php/JAIC
[7] Y. A. Singgalen, “IndoBERT-Based Sentiment Analysis for Understanding Hotel Guests’ Preferences,” Journal of Computer System and Informatics (JoSYC), vol. 6, no. 2, pp. 508–520, 2025, doi: 10.47065/josyc.v6i2.6864.
[8] K. C. Pradhisa and R. Fajriyah, “Analisis Sentimen Ulasan Pengguna E-commerce di Google Play Store Menggunakan Metode IndoBERT,” Building of Informatics, Technology and Science (BITS), vol. 6, no. 1, Jun. 2024, doi: 10.47065/bits.v6i1.5247.
[9] H. N. Alfiana, A. Doewes, and B. Widoyono, “Aspect-Based Sentiment Analysis of Access by KAI Application Reviews Using IndoBERT for Multi-Label Classification Tasks,” Jurnal Teknik Informatika (JUTIF), vol. 7, no. 1, pp. 2723–3863, 2026, doi: 10.52436/1.jutif.2026.7.2.5402.
[10] A. Rajan and M. Manur, “Aspect based sentiment analysis using fine-tuned BERT model with deep context features,” IAES International Journal of Artificial Intelligence, vol. 13, no. 2, pp. 1250–1261, Jun. 2024, doi: 10.11591/ijai.v13.i2.pp1250-1261.
[11] S. Wahyu Iriananda, S. Fatriana Kadir, and D. Yauzan Tusianto, “Analisis Sentimen Berbasis Aspek Pada Aplikasi Bank Digital Indonesia Menggunakan Machine Learning,” 2025, [Online]. Available: http://ocs.ciastech.widyagama.ac.idProceedinghomepage:http://publishing-widyagama.ac.id/ejournal-v2/index.php/ciastech/index
[12] R. A. Rizquna, N. Y. Setiawan, and M. C. Saputra, “Evaluasi Layanan Kedai Makmur Melalui Analisis Sentimen Berbasis Aspek Menggunakan Pendekatan Rule-Based dan Model IndoBERT,” 2026. [Online]. Available: http://j-ptiik.ub.ac.id
[13] J. Šmíd and P. Přibáň, “Prompt-Based Approach for Czech Sentiment Analysis,” Aug. 2025, [Online]. Available: http://arxiv.org/abs/2508.08651
[14] M. J. J. Bucher and M. Martini, “Fine-Tuned ‘Small’ LLMs (Still) Significantly Outperform Zero-Shot Generative AI Models in Text Classification,” Aug. 2024, [Online]. Available: http://arxiv.org/abs/2406.08660
[15] A. Jazuli, Widowati, and R. Kusumaningrum, “Aspect-based sentiment analysis on student reviews using the Indo-Bert base model,” in E3S Web of Conferences, EDP Sciences, Nov. 2023. doi: 10.1051/e3sconf/202344802004.
[16] I. Saputra and G. Leonarde Ginting, “Sentiment Analysis of Tokopedia Customer Reviews using IndoBERT and SMOTE for Class Imbalance Handling,” Journal of Computer System and Informatics (JoSYC), vol. 7, no. 1, pp. 20–27, 2025, doi: 10.47065/josyc.v7i1.8748.
[17] C. Zhao, R. Feng, X. Sun, L. Shen, J. Gao, and Y. Wang, “Enhancing aspect-based sentiment analysis with BERT-driven context generation and quality filtering,” Natural Language Processing Journal, vol. 7, Jun. 2024, doi: 10.1016/j.nlp.2024.100077.
[18] O. Rainio, J. Teuho, and R. Klén, “Evaluation metrics and statistical tests for machine learning,” Sci. Rep., vol. 14, no. 1, Dec. 2024, doi: 10.1038/s41598-024-56706-x.
[19] S. Imron, E. I. Setiawan, and J. Santoso, “Deteksi Aspek Review E-Commerce Menggunakan IndoBERT Embedding dan CNN,” Journal of Intelligent System and Computation, vol. 5, no. 1, pp. 10–16, Apr. 2023, doi: 10.52985/insyst.v5i1.267.
[20] E. Yulianti and N. K. Nissa, “ABSA of Indonesian customer reviews using IndoBERT: single-sentence and sentence-pair classification approaches,” Bulletin of Electrical Engineering and Informatics, vol. 13, no. 5, pp. 3579–3589, Oct. 2024, doi: 10.11591/eei.v13i5.8032.
[21] N. Pantelaios and A. Kapravelos, “Manifest V3 Unveiled: Navigating the New Era of Browser Extensions,” Apr. 2024, doi: 10.14722/madweb.2024.23080.