Utilization of IndoBERT Representation and Random Forest for Sentiment Analysis on User Reviews of Halodoc Pharmacy Services in Google Play

Hendry Fonda; Herianto; Yuda Irawan

doi:10.36378/jtos.v8i2.4822

Hendry Fonda Universitas Hang Tuah Pekanbaru
Herianto Universitas Hang Tuah Pekanbaru
Yuda Irawan Universitas Hang Tuah Pekanbaru

DOI: https://doi.org/10.36378/jtos.v8i2.4822

Keywords: Sentiment Analysis, IndoBERT, Random Forest, Google Play User Reviews

Abstract

With the growing use of digital healthcare platforms such as Halodoc, maintaining consistent service quality that meets user expectations is essential. User reviews on platforms like Google Play provide valuable insights into user perceptions. This study aims to classify user sentiments toward Halodoc’s pharmacy services based on reviews obtained through web scraping from the Google Play Store. The analysis employs the pre-trained IndoBERT model to extract textual features, followed by sentiment classification using the Random Forest algorithm. This combination was selected for its efficiency with limited hardware resources and small dataset size. To enhance data diversity and minimize overfitting, simple augmentation methods such as random word deletion and synonym substitution were implemented. The expected outcomes include an effective sentiment classification model and visualizations of sentiment distributions (positive, negative, neutral). Furthermore, the study contributes to the development of sentiment analysis techniques for Indonesian-language data through an efficient and contextually relevant approach. The research outputs target publication in a nationally accredited (Sinta 4) journal and Intellectual Property Rights (IPR) registration. Ultimately, this study is expected to support the improvement of technology-based pharmacy services through the strategic application of machine learning.

Downloads

Download data is not yet available.

References

. Ardiansyah, Adika Sri Widagdo, Krisna Nuresa Qodri, Saputro FEN, Nisrina Akbar Rizky P. Analisis sentimen terhadap pelayanan Kesehatan berdasarkan ulasan Google Maps menggunakan BERT. J Fasilkom. 2023;13(02):326–33.

. Geni L, Yulianti E, Sensuse DI. Sentiment Analysis of Tweets Before the 2024 Elections in Indonesia Using IndoBERT Language Models. J Ilm Tek Elektro Komput dan Inform [Internet]. 2023;9(3):746–57. Available from: http://journal.uad.ac.id/index.php/JITEKI R. Nancy Deborh MSARGGGISJJJ. IRJET- Sentiment Analysis and Machine Learning Algorithm Implementation on Health Care System. Irjet. 2021;8(5):3466–71.

. Fikry M, Oktavia L, Dwi Arista T, Islam Negeri Sultan Syarif Kasim Riau U, Soebrantas NoKm JH, Baru S. Klasifikasi Sentimen Masyarakat di Twitter terhadap Kenaikan Harga BBM dengan Metode K-NN Oleh : Tiara Dwi Arista Klasifikasi Sentimen Masyarakat di Twitter terhadap Kenaikan Harga BBM dengan Metode K-NN. JUKI J Komput dan Inform. 2023;5.

. Desai A, Kalaskar S, Kumbhar O, Dhumal R. Cyber Bullying Detection on Social Media using Machine Learning. ITM Web Conf. 2021;40:03038.

. Singgalen YA. Performance Analysis of IndoBERT for Sentiment Classification in Indonesian Hotel Review Data. 2025;6(2):976–86.

. Manajemen J, Informasi S, Hazizah N, Feranika A, Komputer I, Ilmu F, et al. Implementasi Algoritma Random Forest Dalam Klasifikasi Risiko Gagal Bayar Kartu Kredit Pada Nasabah Bank Jurnal Manajemen Teknologi dan Sistem Informasi ( JMS ). 2025;5:1050–9.

. Werdiningsih I, Purwanti E, Wira Aditya GR, Hidayat AR, Athallah RSR, Sahar VA, et al. Identifikasi Penipuan Kartu Kredit Pada Transaksi Ilegal Menggunakan Algoritma Random Forest dan Decision Tree. J Sisfokom (Sistem Inf dan Komputer). 2023;12(3):477–84.

. Werdiningsih I, Purwanti E, Wira Aditya GR, Hidayat AR, Athallah RSR, Sahar VA, et al. Identifying Credit Card Fraud in Illegal Transactions Using Random Forest and Decision Tree Algorithms. J Sisfokom (Sistem Inf dan Komputer). 2023;12(3):477–84.

. Pribadi MR, Manongga D, Purnomo HD, Setyawan I, Hendry. Sentiment Analysis of the PeduliLindungi on Google Play using the Random Forest Algorithm with SMOTE. 2022 Int Semin Intell Technol Its Appl Adv Innov Electr Syst Humanit ISITIA 2022 - Proceeding. 2022;(November):115–9.

. N. Pohan, P. A. Widya Purnama, and H. Kurnia AR, “Pengenalan Aplikasi Teknologi Komputer untuk Edukasi Islami bagi Anak-anak TPQ Nurul Huda Gunung Pangilun, Kota Padang”, MB, vol. 1, no. 3, pp. 99–109, Sep. 2025, Accessed: Oct. 07, 2025. [Online]. Available: https://yasiinpublisher.org/index.php/mandalabakti/article/view/56

. W. Akbar, “Sinergi Mahasiswa Prodi Ilmu Hukum Universitas Islam Kuantan Singingi dan Aparatur Penegak Hukum dalam Mendukung Efektivitas Pelayanan Publik pada Bagian Pemulihan Aset dan Barang Bukti (PAPBB)Kejaksaan Negeri Kuantan Singingi””, MB, vol. 1, no. 3, pp. 110–118, Sep. 2025, Accessed: Oct. 07, 2025. [Online]. Available: https://yasiinpublisher.org/index.php/mandalabakti/article/view/69

. Febri Haswan, Nofri Wandi Al-Hafiz, A. Mualif, Afrinald Rizhan, Yudio Prastio, and Paris Paizal, “Pelatihan Optimalisasi Layanan Berbasis Teknologi: Aplikasi Antrian PTSP dan Sidang di Pengadilan Agama Teluk Kuantan”, MB, vol. 1, no. 3, pp. 119–125, Sep. 2025, Accessed: Oct. 07, 2025. [Online]. Available: https://yasiinpublisher.org/index.php/mandalabakti/article/view/57.

. R. Gomez, F. Chen, and Y. Wang, “Human–AI collaboration for real-time skin cancer screening on smartphones,” npj Digital Medicine, vol. 7, no. 84, pp. 1–10, 2024.

. J. K. Lee and S. H. Park, “Experimental AI research frameworks for medical image analysis,” IEEE Access, vol. 11, pp. 128221–128234, 2023.

. M. Elgendi, C. Lovell, and D. Abbott, “Machine learning experimental design for healthcare applications,” Sensors, vol. 21, no. 22, p. 7551, 2021.

. R. L. Mehta, P. Varghese, and K. Singh, “Designing user-centered interfaces for AI-powered healthcare applications,” IEEE Access, vol. 12, pp. 105321–105334, 2024. doi: 10.1109/ACCESS.2024.105321.

. J. Kim, A. Kumar, and F. Torres, “Evaluating usability in mobile AI healthcare systems: A user-experience perspective,” International Journal of Human–Computer Studies, vol. 179, p. 103087, 2023. doi: 10.1016/j.ijhcs.2023.103087.

. M. Chen, Z. Wang, and J. Xu, “Edge–cloud collaboration architecture for intelligent healthcare systems,” IEEE Internet of Things Journal, vol. 11, no. 2, pp. 2134–2148, 2024.

. H. Zhang, F. Li, and T. Nguyen, “A modular AI pipeline for mobile-based medical imaging applications,” IEEE Access, vol. 12, pp. 114521–114533, 2024.

. S. Das, R. Banerjee, and K. Huang, “Deep learning infrastructure for real-time medical diagnostics in cloud–mobile ecosystems,” ACM Transactions on Computing for Healthcare, vol. 5, no. 1, pp. 1–15, 2023.

. L. Martins, A. Costa, and R. Pereira, “Applying UML modeling in mobile health application development: A design-oriented approach,” IEEE Access, vol. 12, pp. 120453–120465, 2024.

. T. Nguyen and S. Patel, “Model-driven engineering and UML-based design for AI-enabled mobile systems,” Journal of Software Engineering and Applications, vol. 17, no. 2, pp. 75–89, 2023.

. A. Kumar, S. R. Gupta, and L. Zhang, “UML activity diagram modeling for AI-driven mobile healthcare applications,” IEEE Access, vol. 12, pp. 125231–125245, 2024.

. R. Lopez and M. Fernandes, “Workflow modeling in mobile intelligent systems using UML activity diagrams,” Journal of Systems and Software Engineering, vol. 196, pp. 112015, 2023.

. J. Fernandez, L. Silva, and P. R. Costa, “UML class modeling for modular AI-driven healthcare applications,” IEEE Access, vol. 12, pp. 130512–130528, 2024.