Analisis Komparatif Kinerja IndoBERT dan XLM-RoBERTa Dalam Analisis Sentimen Ulasan Google Maps Mitra10 Siliwangi Pamulang
-
Rizki Reza
*
Universitas Pamulang, Banten,
Indonesia
- Sajarwo Anggai Universitas Pamulang, Banten, Indonesia
- Abu Khalid Rivai Universitas Pamulang, Banten, Indonesia (*) Corresponding Author
Abstract
Google Maps customer reviews provide rich information about shopping experiences, but the growing volume of unstructured text makes manual analysis inefficient. This study classifies customer-review sentiment for Mitra10 Siliwangi Pamulang and compares IndoBERT, an Indonesian monolingual language model, with XLM-RoBERTa, a multilingual model. A total of 1,305 reviews were collected through web scraping and categorized into positive, neutral, and negative sentiment. Data processing included selection, duplicate removal, case folding, text-format normalization, tokenization, a maximum input length of 128 tokens, and dataset splitting into 1,043 training samples, 131 validation samples, and 131 test samples. Class imbalance was handled using class weighting in weighted CrossEntropyLoss without oversampling. Both models were fine-tuned with identical settings: 5 epochs, batch size 8, learning rate 2×10⁻⁵, AdamW optimizer, and random seed 42. XLM-RoBERTa achieved 96.95% accuracy, 97.25% weighted precision, 96.95% weighted recall, and a 97.07% weighted F1-score. IndoBERT achieved 95.42% accuracy, 96.90% weighted precision, 95.42% weighted recall, and a 95.88% weighted F1-score. Although XLM-RoBERTa was numerically 1.53 percentage points higher in accuracy, the exact McNemar test produced a p-value of 0.625, indicating no statistically significant difference on the test set. Both models therefore performed strongly on this dataset; however, the negative class should be interpreted cautiously because only 40 of the 1,305 reviews were negative.
Downloads
References
N. Al Hafidh and A. Al-Karawi , “Advanced sentiment analysis of Amazon electronics reviews leveraging BERT: Model optimization and evaluation,” Procedia Computer Science, vol. 258, pp. 3608–3618, 2025, https://doi.org/10.1016/j.procs.2025.04.616
A. Erfina and N. R. Wardani, “Analisis sentimen perguruan tinggi termewah di Indonesia menurut ulasan Google Maps menggunakan Support Vector Machine (SVM),” Jurnal Manajemen Informatika dan Sistem Informasi, vol. 5, no. 1, pp. 77–85, 2022, https://doi.org/10.36595/misi.v5i1.591
J. Ipmawati, Saifulloh, and Kusnawi, “Analisis sentimen tempat wisata berdasarkan ulasan pada Google Maps menggunakan algoritma Support Vector Machine,” MALCOM: Indonesian Journal of Machine Learning and Computer Science, vol. 4, no. 1, pp. 247–256, 2024, https://doi.org/10.57152/malcom.v4i1.1066
T. Z. Fatikhah, M. Muhtarom, and I. Oktaviani, “Analisis sentimen ulasan Mie Gacoan Solo Veteran di Google Maps menggunakan algoritma Naive Bayes,” ZONAsi: Jurnal Sistem Informasi, vol. 6, no. 3, pp. 649–658, 2024, https://doi.org/10.31849/zn.v6i3.21194
A. C. T. Angel, V. H. Pranatawijaya, and Widiatry, “Analisis sentimen dan emosi dari ulasan Google Maps untuk layanan rumah sakit di Palangka Raya menggunakan machine learning,” KONSTELASI, vol. 4, no. 1, pp. 35–49, 2024, https://doi.org/10.24002/konstelasi.v4i1.8924
Ardiansyah, A. S. Widagdo, K. N. Qodri, F. E. N. Saputro, and N. A. Rizky P., “Analisis sentimen terhadap pelayanan kesehatan berdasarkan ulasan Google Maps menggunakan BERT,” Jurnal Fasilkom, vol. 13, no. 2, pp. 326–333, 2023, https://doi.org/10.37859/jf.v13i02.5170
V. Chandradev, I. M. A. D. Suarjaya, and I. P. A. Bayupati, “Analisis sentimen review hotel menggunakan metode deep learning BERT,” Jurnal Buana Informatika, vol. 14, no. 2, pp. 107–116, 2023, https://doi.org/10.24002/jbi.v14i02.7244
A. F. Setyawan, A. D. P. Ariyanto, F. K. Fikriah, and R. I. Nugraha, “Analisis sentimen ulasan iPhone di Amazon menggunakan model deep learning BERT berbasis transformer,” Elkom: Jurnal Elektronika dan Komputer, vol. 17, no. 2, pp. 447–452, 2024, https://doi.org/10.51903/elkom.v17i2.2150
G. Z. Nabiilah, S. Y. Prasetyo, Z. N. Izdihar, and A. S. Girsang, “BERT base model for toxic comment analysis on Indonesian social media,” Procedia Computer Science, vol. 216, pp. 714–721, 2023, https://doi.org/10.1016/j.procs.2022.12.188
G. P. Satria, K. S. Gunawan, and Z. E. Rasjid, “Aspect-based sentiment analysis of multilingual customer product reviews: Leveraging unsupervised aspect extraction with ABAE for XLM-RoBERTa-based classification,” Procedia Computer Science, vol. 269, pp. 239–248, 2025, https://doi.org/10.1016/j.procs.2025.08.276
N. A. Wahyuni, D. P. Ayu, and H. Irsyad, “Analisis sentimen di YouTube terhadap kenaikan UKT menggunakan metode Support Vector Machine,” Arcitech: Journal of Computer Science and Artificial Intelligence, vol. 4, no. 1, pp. 57–71, 2024, https://doi.org/10.29240/arcitech.v4i1.10829
F. Bouchra, I. M. A. D. Suarjaya, and N. K. D. Rusjayanthi, “Analisis sentimen masyarakat terhadap tayangan televisi nasional menggunakan metode deep learning,” Jurnal Buana Informatika, vol. 15, no. 2, pp. 89–99, 2024, https://doi.org/10.24002/jbi.v15i2.9118
A. Y. Lubis and M. Y. H. Setyawan, “Analisis sentimen terhadap aplikasi Pospay menggunakan algoritma Support Vector Machine dan Naive Bayes,” Jurnal Teknologi dan Sistem Informasi Bisnis, vol. 6, no. 3, pp. 514–521, 2024, https://doi.org/10.47233/jteksis.v6i3.1310
R. A. Husen, R. Astuti, L. Marlia, Rahmaddeni, and L. Efrizoni, “Analisis sentimen opini publik pada Twitter terhadap Bank BSI menggunakan algoritma machine learning,” MALCOM: Indonesian Journal of Machine Learning and Computer Science, vol. 3, no. 2, pp. 211–218, 2023, https://doi.org/10.57152/malcom.v3i2.901
A. F. Pangestu, B. Rahmat, and A. N. Sihananto, “Analisis sentimen pada media sosial X terhadap implementasi Kurikulum Merdeka menggunakan metode FastText dan Long Short-Term Memory (LSTM),” JIPI, vol. 9, no. 4, pp. 2271–2280, 2024, https://doi.org/10.29100/jipi.v9i4.5665
L. Damayanti and K. M. Lhaksmana, “Sentiment analysis of the 2024 Indonesia presidential election on Twitter,” Sinkron: Jurnal dan Penelitian Teknik Informatika, vol. 8, no. 2, pp. 938–946, 2024, https://doi.org/10.33395/sinkron.v8i2.13379
M. J. Islam, R. Datta, and A. Iqbal, “Actual rating calculation of the Zoom Cloud Meetings app using user reviews on Google Play Store with sentiment annotation of BERT and hybridization of RNN and LSTM,” Expert Systems with Applications, vol. 223, Art. no. 119919, 2023, https://doi.org/10.1016/j.eswa.2023.119919
A. Rehman, K. Das, Kamlish, and F. Abid, “Sentiment analysis using bidirectional encoder representations from transformers,” Proceedings of the Pakistan Academy of Sciences: A. Physical and Computational Sciences, vol. 61, no. 2, pp. 153–165, 2024, https://doi.org/10.53560/PPASA(61-2)870
K. Kusnawi and K. Anam, “Comparison of sentiment labeling using TextBlob, VADER, and Flair in public opinion analysis post-2024 presidential inauguration with IndoBERT,” Jurnal Teknik Informatika (JUTIF), vol. 6, no. 2, pp. 803–818, Apr. 2025, https://doi.org/10.52436/1.jutif.2025.6.2.4015
S. L. Mirtaheri, A. Pugliese, N. Movahed, and R. Shahbazian, “A comparative analysis on using GPT and BERT for automated vulnerability scoring,” Intelligent Systems with Applications, vol. 26, Art. no. 200515, 2025, https://doi.org/10.1016/j.iswa.2025.200515
D. R. Alghifari, M. Edi, and L. Firmansyah, “Implementasi Bidirectional LSTM untuk analisis sentimen terhadap layanan Grab Indonesia,” Jurnal Manajemen Informatika (JAMIKA), vol. 12, no. 2, pp. 89–99, 2022, https://doi.org/10.34010/jamika.v12i2.7764
S. Nachwa et al., “Pendekatan klasifikasi dalam knowledge discovery untuk analisis sentimen berbasis aspek pada ulasan Bandara Sultan Mahmud Badaruddin II di Google Maps,” JATI: Jurnal Mahasiswa Teknik Informatika, vol. 9, no. 3, pp. 4782–4789, 2025, https://doi.org/10.36040/jati.v9i3.13776
Y. Romadhoni and K. F. H. Holle, “Analisis sentimen terhadap PERMENDIKBUD No. 30 pada media sosial Twitter menggunakan metode Naive Bayes dan LSTM,” Jurnal Informatika: Jurnal Pengembangan IT, vol. 7, no. 2, pp. 118–124, 2022, https://doi.org/10.30591/jpit.v7i2.3191
L. Rofiqi and M. Akbar, “Analisis sentimen terkait RUU Perampasan Aset dengan Support Vector Machine,” JEKIN: Jurnal Teknik Informatika, vol. 4, no. 3, pp. 529–538, 2024, https://doi.org/10.58794/jekin.v4i3.824
S. P. Azzahra, Y. A. Apriyanto, and A. Wijaya, “Analisis sentimen ulasan aplikasi DeepL pada Google Play dengan metode Support Vector Machine (SVM),” Jurnal Sistem Informasi (JUSIN), vol. 4, no. 2, pp. 59–66, 2023, https://doi.org/10.32546/jusin.v4i2.2368
N. P. V. D. Saraswati, N. Yudistira, and P. P. Adikara, “Analisis sentimen terhadap perundungan siber pada Twitter menggunakan algoritma Bidirectional Encoder Representations from Transformer (BERT),” Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer, vol. 7, no. 2, pp. 909–916,2023.
A. Supian, B. T. Revaldo, N. Marhadi, L. Efrizoni, and Rahmaddeni, “Perbandingan kinerja Naive Bayes dan SVM pada analisis sentimen Twitter Ibukota Nusantara,” Jurnal Ilmiah Informatika, vol. 12, no. 1, pp. 15–21, 2024, https://doi.org/10.33884/jif.v12i01.8721
M. Yasir and R. Suraji, “Perbandingan metode klasifikasi Naive Bayes, Decision Tree, Random Forest terhadap analisis sentimen kenaikan biaya haji 2023 pada media sosial YouTube,” Jurnal Cahaya Mandalika, vol. 3, no. 2, pp. 180–192, 2023, https://doi.org/10.36312/jcm.v3i2.1520
J. E. Bata, Istiadi, and S. W. Iriananda, “Analisis sentimen ulasan pengunjung wisata Laguna Waikuri pada Google Maps menggunakan multi kelas Support Vector Machine,” JATI: Jurnal Mahasiswa Teknik Informatika, vol. 8, no. 6, pp. 11115–11123, 2024, https://doi.org/10.36040/jati.v8i6.11229
D. S. Utami, A. Erfina, and Mupaat, “Analisis sentimen ulasan terkait UNESCO Global Geopark di Google Maps dengan algoritma Naive Bayes,” J-SAKTI: Jurnal Sains Komputer dan Informatika, vol. 6, no. 2, pp. 1154–1170, 2022.
Bila bermanfaat silahkan share artikel ini
Berikan Komentar Anda terhadap artikel Analisis Komparatif Kinerja IndoBERT dan XLM-RoBERTa Dalam Analisis Sentimen Ulasan Google Maps Mitra10 Siliwangi Pamulang
Pages: 25-34
Copyright (c) 2026 Rizki Reza, Sajarwo Anggai, Abu Khalid Rivai
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).
