Klasifikasi Sentimen terhadap Layanan BPJS Menggunakan Model Hybrid IndoBERT dan Random Forest
DOI:
https://doi.org/10.30865/json.v7i2.9321Keywords:
Analisis Sentimen, IndoBERT, Transfer Learning, Random Forest, Layanan Publik Digital, klasifikasi teksAbstract
Analisis sentimen terhadap opini publik di media sosial merupakan alat yang krusial bagi penyedia layanan seperti BPJS Kesehatan untuk mengevaluasi kualitas layanannya. Pendekatan yang akurat seperti fine-tuning model transformer IndoBERT seringkali terkendala oleh kebutuhan sumber daya komputasi yang tinggi. Penelitian ini membandingkan dua pendekatan berbasis IndoBERT: fine-tuning end-to-end dan transfer learning dengan ekstraksi fitur yang diklasifikasikan menggunakan Random Forest (RF). Eksperimen menggunakan 3.059 komentar berbahasa Indonesia terkait layanan BPJS yang telah dilabeli. Hasilnya menunjukkan bahwa model hybrid IndoBERT + RF secara signifikan mengungguli model fine-tuning secara keseluruhan. Model hybrid mencapai akurasi 98% dan F1-score tertimbang 0,98, dibandingkan dengan model fine-tuning yang hanya mencapai 92% dan 0,92. Selain itu, model hybrid menunjukkan peningkatan kinerja yang mencolok pada kelas minoritas (netral dan positif) serta jauh lebih efisien dalam waktu komputasi, dengan waktu pelatihan dan evaluasi hanya 33 detik berbanding 206 detik pada model end-to-end. Temuan ini membuktikan bahwa strategi transfer learning ringan berbasis IndoBERT tidak hanya mempertahankan akurasi tinggi tetapi juga menawarkan efisiensi sumber daya yang luar biasa, sehingga menjadi solusi yang sangat layak untuk implementasi sistem pemantauan opini publik di institusi dengan infrastruktur terbatas.
References
A. Rolangon, A. Weku, and G. A. Sandag, “Perbandingan Algoritma LSTM Untuk Analisis Sentimen Pengguna Twitter Terhadap Layanan Rumah Sakit Saat Pandemi Covid-19,” TeIKa, vol. 13, no. 01, pp. 31–40, May 2023, doi: 10.36342/teika.v13i01.3063.
Y. Kornitasari, L. J. Sura, and D. N. A. M. Dewi, “How cybercrime sentiment shapes mobile banking adoption in Islamic banking,” J. Ekon. Keuang. Islam, vol. 10, no. 2, pp. 217–232, Jul. 2024, doi: 10.20885/JEKI.vol10.iss2.art6.
M. S. Alam, M. S. H. Mrida, and M. A. Rahman, “Sentiment Analysis in Social Media: How Data Science Impacts Public Opinion Knowledge Integrates Natural Language Processing (Nlp) With Artificial Intelligence (Ai),” Am. J. Sch. Res. Innov., vol. 4, no. 1, pp. 63–100, 2025, doi: 10.63125/r3sq6p80.
T. Masiya and S. Lubinga, “The Influence of Social Media on the Transparency and Accountability of the South African Public Sector,” Stud. Media Commun., vol. 11, no. 7, pp. 42–56, 2023, doi: 10.11114/SMC.V11I7.6151.
A. F. Hidayatullah, R. A. Apong, D. T. C. Lai, and A. Qazi, “Pre-trained language model for code-mixed text in Indonesian, Javanese, and English using transformer,” Soc. Netw. Anal. Min., vol. 15, no. 1, 2025, doi: 10.1007/s13278-025-01444-9.
L. Geni, E. Yulianti, and D. I. Sensuse, “Sentiment Analysis of Tweets Before the 2024 Elections in Indonesia Using IndoBERT Language Models,” J. Ilm. Tek. Elektro Komput. dan Inform., vol. 9, no. 3, pp. 746–757, 2023, doi: 10.26555/jiteki.v9i3.26490.
A. F. Hidayatullah, “Code-Mixed Sentiment Analysis on Indonesian-Javanese-English Text Using Transformer Models,” 2024 8th Int. Conf. Inf. Technol. Inf. Syst. Electr. Eng. ICITISEE 2024, no. August, pp. 340–345, 2024, doi: 10.1109/ICITISEE63424.2024.10730138.
R. I. Perwira, V. A. Permadi, D. I. Purnamasari, and R. P. Agusdin, “Domain-Specific Fine-Tuning of IndoBERT for Aspect-Based Sentiment Analysis in Indonesian Travel User-Generated Content,” J. Inf. Syst. Eng. Bus. Intell., vol. 11, no. 1, pp. 30–40, 2025, doi: 10.20473/jisebi.11.1.30-40.
M. I. Sari and L. H. Suadaa, “Study of the Application of Text Augmentation with Paraphrasing to Overcome Imbalanced Data in Indonesian Text Classification,” J. Online Inform., vol. 10, no. 1, pp. 132–142, Apr. 2025, doi: 10.15575/join.v10i1.1472.
W. Wongso, H. Lucky, and D. Suhartono, “Pre-trained transformer-based language models for Sundanese,” J. Big Data, vol. 9, no. 1, p. 39, Dec. 2022, doi: 10.1186/s40537-022-00590-7.
N. Crosley and I. Wasito, “Improving IT Support Efficiency Using AI-Driven Ticket Random Forest Classification Technique,” Sinkron, vol. 8, no. 4, pp. 2283–2293, 2023, doi: 10.33395/sinkron.v8i4.12925.
N. Jalal, A. Mehmood, G. S. Choi, and I. Ashraf, “A novel improved random forest for text classification using feature ranking and optimal number of trees,” J. King Saud Univ. - Comput. Inf. Sci., vol. 34, no. 6, pp. 2733–2742, 2022, doi: 10.1016/j.jksuci.2022.03.012.
B. N. Pikir, M. K. Anam, H. Asnal, Rahmaddeni, T. A. Fitri, and Hamdani, “Sentiment Analysis of Technology Utilization by Pekanbaru City Government Based on Community Interaction in Social Media,” JAIA - J. Artif. Intell. Appl., vol. 2, no. 1, pp. 32–40, 2021, doi: 10.33372/jaia.v2i1.795.
O. Alqaryouti, N. Siyam, A. Abdel Monem, and K. Shaalan, “Aspect-based sentiment analysis using smart government review data,” Appl. Comput. Informatics, vol. 20, no. 1–2, pp. 142–161, 2024, doi: 10.1016/j.aci.2019.11.003.
A. Elhan, M. K. D. Hardhienata, Y. Herdiyeni, S. H. Wijaya, and J. Adisantoso, “Analisis Sentimen Pengguna Twitter terhadap Vaksinasi COVID-19 di Indonesia menggunakan Algoritme Random Forest dan BERT,” J. Ilmu Komput. dan Agri-Informatika, vol. 9, no. 2, pp. 199–211, Nov. 2022, doi: 10.29244/jika.9.2.199-211.
A. Jazuli, Widowati, and R. Kusumaningrum, “Aspect-based sentiment analysis on student reviews using the Indo-Bert base model,” E3S Web Conf., vol. 448, pp. 1–10, 2023, doi: 10.1051/e3sconf/202344802004.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2025 Jurnal Sistem Komputer dan Informatika (JSON)

This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.

This work is licensed under a Creative Commons Attribution 4.0 International License
Authors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under Creative Commons Attribution 4.0 International License that allows others to share the work with an acknowledgment of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgment of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (Refer to The Effect of Open Access).

