Aspect-Based Sentiment Analysis of Hospital Service Reviews Using Fine-Tuned IndoBERT
DOI:
https://doi.org/10.30871/jaic.v9i5.10765Keywords:
Aspect-Based Sentiment Analysis, Fine-Tuning, Google Review, IndoBERTAbstract
Aspect-Based Sentiment Analysis (ABSA) has become a crucial approach for extracting detailed opinions from user-generated content, especially in the healthcare domain. This study analyzes public sentiment toward hospital services in Indonesia using IndoBERT, fine-tuned on 2.448 reviews collected from Google Reviews and Instagram. Sentiment labels were automatically assigned with a pre-trained Indonesian RoBERTa classifier, while aspect extraction was performed through a lexicon-based approach covering five service dimensions: Facilities, Staff Competence, Empathy and Communication, Reliability and Responsiveness, and Cost and Affordability. To address class imbalance, the IndoBERT model was optimized using class weight adjustments. The results demonstrate strong performance, achieving an overall accuracy of 96%. In terms of sentiment classification, the model obtained F1-scores of 89% for negative, 83% for neutral, and 99% for positive sentiment, with a macro-average F1 of 90%. By aspect, Facilities (82.24%) and Empathy & Communication (91.71%) received the highest positive sentiment, while Cost & Affordability recorded the highest proportion of negative sentiment (25%). These findings underscore the effectiveness of IndoBERT-based ABSA in capturing nuanced public perceptions and highlight its potential as a decision-support tool for hospitals to enhance service quality and patient satisfaction in Indonesia.
Downloads
References
[1] X. Li, L. Chen, B. Chen, and X. Ge, “BERT-BiLSTM-Attention model for sentiment analysis on Chinese stock reviews,” Applied Mathematics and Nonlinear Sciences, vol. 9, no. 1, Jan. 2024, doi: 10.2478/amns-2024-1847.
[2] A. Bansal and N. Kumar, “Aspect-Based Sentiment Analysis Using Attribute Extraction of Hospital Reviews,” New Gener Comput, vol. 40, no. 4, pp. 941–960, Dec. 2022, doi: 10.1007/s00354-021-00141-3.
[3] D. Singh, S. Shivprakash Barve, and A. Krishna Dwivedi, “OptiASAR: Optimized Aspect-Based Sentiment Analysis of Reviews With BiLSTM-GRU and NER-BERT in Healthcare Decision-Making,” IEEE Access, vol. 13, pp. 47459–47474, 2025, doi: 10.1109/ACCESS.2025.3549303.
[4] Suhariyanto, R. Sarno, C. Fatichah, and R. Abdullah, “Aspect-based sentiment analysis: natural language understanding for implicit review,” Dec. 01, 2024, Institute of Advanced Engineering and Science. doi: 10.11591/ijece.v14i6.pp6711-6722.
[5] A. C. T Angel and V. H. Pranatawijaya, “Analisis Sentimen dan Emosi dari Ulasan Google Maps untuk Layanan Rumah Sakit di Palangka Raya Menggunakan Machine Learning,” 2024.
[6] A. Rolangon et al., “Perbandingan Algoritma LSTM Untuk Analisis Sentimen Pengguna Twitter Terhadap Layanan Rumah Sakit Saat Pandemi Covid-19 The Comparison of LSTM Algorithms for Twitter User Sentiment Analysis on Hospital Services During the Covid-19 Pandemic.”
[7] A. Sri Widagdo et al., “Analisis sentimen terhadap pelayanan Kesehatan berdasarkan ulasan Google Maps menggunakan BERT”.
[8] T. Dzulkarnain, D. E. Ratnawati, and B. Rahayudi, “Penggunaan Metode Naïve Bayes Classifier pada Analisis Sentimen Penilaian Masyarakat Terhadap Pelayanan Rumah Sakit di Malang,” Jurnal Teknologi Informasi dan Ilmu Komputer, vol. 11, no. 5, pp. 993–1000, Oct. 2024, doi: 10.25126/jtiik.2024117979.
[9] H. Imaduddin, F. Yusfida A’la, and Y. S. Nugroho, “Sentiment Analysis in Indonesian Healthcare Applications using IndoBERT Approach.” [Online]. Available: www.ijacsa.thesai.org
[10] A. F. RIZKI, W. Prihartono, and F. Rohman, “Analisis Sentimen Ulasan Google Maps Rumah Sakit Khalishah Di Cirebon Dengan Algoritma Naive Bayes,” Jurnal Informatika dan Teknik Elektro Terapan, vol. 13, no. 2, Apr. 2025, doi: 10.23960/jitet.v13i2.6309.
[11] E. I. Setiawan, P. Tjendika, J. Santoso, F. X. Ferdinandus, Gunawan, and K. Fujisawa, “Aspect-Based Sentiment Analysis of Healthcare Reviews from Indonesian Hospitals based on Weighted Average Ensemble,” Journal of Applied Data Sciences, vol. 5, no. 4, pp. 1579–1596, Dec. 2024, doi: 10.47738/jads.v5i4.328.
[12] A. N. Azhar and M. L. Khodra, Fine-tuning Pretrained Multilingual BERT Model for Indonesian Aspect-based Sentiment Analysis. IEEE, 2020.
[13] F. Koto, A. Rahimi, J. H. Lau, and T. Baldwin, “IndoLEM and IndoBERT: A Benchmark Dataset and Pre-trained Language Model for Indonesian NLP,” Online. [Online]. Available: https://huggingface.co/
[14] Dhendra and V. Gayuh Utomo, “Benchmarking IndoBERT and Transformer Models for Sentiment Classification on Indonesian E-Government Service Reviews,” Jurnal Transformatika, vol. 23, no. 1, pp. 86–95, Jul. 2025, doi: 10.26623/transformatika.v23i1.12095.
[15] A. A. Azhari, Y. Sibaroni, and S. S. Prasetiyowati, “Detection of Indonesian Hate Speech in the Comments Column of Indone-sian Artists’ Instagram Using the RoBERTa Method,” JIPI (Jurnal Ilmiah Penelitian dan Pembelajaran Informatika), vol. 8, no. 3, pp. 764–773, Aug. 2023, doi: 10.29100/jipi.v8i3.3898.
[16] L. Simanihuruk and H. Suparwito, “Long Short-Term Memory and Bidirectional Long Short-Term Memory Algorithms for Sentiment Analysis of Skintific Product Reviews,” ITM Web of Conferences, vol. 71, p. 01016, 2025, doi: 10.1051/itmconf/20257101016.
[17] 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
[18] V. Vinardo and I. Wasito, “Two-Stage Sentiment Analysis on Indonesian Online News Using Lexicon-Based,” sinkron, vol. 8, no. 4, pp. 2109–2119, Oct. 2023, doi: 10.33395/sinkron.v8i4.12769.
[19] R. Randy Suryono, “Sentiment Classification of Indonesian-Language Roblox Reviews Using IndoBERT with SMOTE Optimization,” 2025. [Online]. Available: http://jurnal.polibatam.ac.id/index.php/JAIC
[20] Mahfudhoh and I. Muslimin, “Pengaruh Kualitas Pelayanan Terhadap Kepuasan Pasien Pada Rumah Sakit Umum Daerah Kota Cilegon,” Jurnal Ilmiah Manajemen, vol. Vol. 8 No. 1, 2020, Apr. 2020.
[21] M. C. Huwae et al., “Analysis of Inpatient Care Service Quality in Hospitals Based on National Standards: A Literature Review,” Healthy Tadulako Journal (Jurnal Kesehatan Tadulako, vol. 11, no. 1, 2025.
[22] A. Diaz Pratama, K. P. Legawa, N. Waya, and I. Bernarto, “The Effect Of Hospital Service Management Quality On Patient Satisfaction At Siloam Lippo Village Hospital Building B Karawaci,” 2024.
[23] F. Farias, T. Ludermir, and C. Bastos-Filho, “Similarity Based Stratified Splitting: an approach to train better classifiers,” Oct. 2020, [Online]. Available: http://arxiv.org/abs/2010.06099
[24] H. T. Madabushi, E. Kochkina, and M. Castelle, “Cost-Sensitive BERT for Generalisable Sentence Classification with Imbalanced Data,” Mar. 2020, [Online]. Available: http://arxiv.org/abs/2003.11563
[25] S. Rahmawati, A. Wibowo, and A. F. N. Masruriyah, “Improving Diabetes Prediction Accuracy in Indonesia: A Comparative Analysis of SVM, Logistic Regression, and Naive Bayes with SMOTE and ADASYN,” Jurnal RESTI, vol. 8, no. 5, pp. 607–614, Oct. 2024, doi: 10.29207/resti.v8i5.5980.
[26] H. Hikmayanti, A. F. Nurmasruriyah, A. Fauzi, N. Nurjanah, and A. Nur Rani, “Performance Comparison of Support Vector Machine Algorithm and Logistic Regression Algorithm,” International Journal of Artificial Intelegence Research, vol. 7, no. 1, p. 1, 2023, doi: 10.29099/ijair.v7i1.1.1114.
[27] A. Nurpiana and A. W. Wijayanto, “Comparison of Models for Classification of Learning Achievement of Middle School Students in Indonesia in 2019 using the Support Vector Machine Algorithm, Conditional Inference Trees, and Random Forest,” Jurnal Matematika, Statistika dan Komputasi, vol. 18, no. 3, pp. 447–455, May 2022, doi: 10.20956/j.v18i3.19208.
[28] 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.
[29] Y. Asri, D. Kuswardani, W. N. Suliyanti, Y. O. Manullang, and A. R. Ansyari, “Sentiment analysis based on Indonesian language lexicon and IndoBERT on user reviews PLN mobile application,” Indonesian Journal of Electrical Engineering and Computer Science, vol. 38, no. 1, p. 677, Apr. 2025, doi: 10.11591/ijeecs.v38.i1.pp677-688.
[30] J. Devlin, M.-W. Chang, K. Lee, and K. Toutanova, “BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding,” May 2019, [Online]. Available: http://arxiv.org/abs/1810.04805
[31] H. Kaur and D. Kaur Sandhu, “Evaluating the Effectiveness of the Proposed System Using F1 Score, Recall, Accuracy, Precision and Loss Metrics Compared to Prior Techniques,” International Journal of Communication Networks and Information Security, no. Volume 15 Issue 04 Year 2023, Dec. 2023, [Online]. Available: https://ijcnis.org
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2025 Aulia Maretta, Allsela Meiriza
This work is licensed under a Creative Commons Attribution-ShareAlike 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 a Creative Commons Attribution License (Attribution-ShareAlike 4.0 International (CC BY-SA 4.0) ) that allows others to share the work with an acknowledgement 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 acknowledgement 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 (See The Effect of Open Access).
