Pengembangan Model Analisis Sentimen Teradaptasi Budaya untuk UMKM Indonesia: Pendekatan Mixed-Method dengan IndoBERT : Development of Culturally-Adapted Sentiment Analysis Model for Indonesian SMEs: A Mixed-Method Approach with IndoBERT

Deshandra Afga Nagara; Sugeng Rifqi Mubaroq

doi:10.57152/malcom.v6i3.2593

Authors

Deshandra Afga Nagara Akademi Digital Bandung
Sugeng Rifqi Mubaroq Akademi Digital Bandung

DOI:

https://doi.org/10.57152/malcom.v6i3.2593

Keywords:

Analisis Sentimen, Indobert, Mixed-Method, Model Teradaptasi Budaya, UMKM Indonesia.

Abstract

Pelaku UMKM Indonesia berhadapan dengan kesulitan memanfaatkan data media sosial sebagai pijakan pengambilan keputusan bisnis. Sekalipun 99,9% pelaku usaha tanah air berstatus UMKM, kapasitas mereka mengurai sentimen konsumen secara sistematis tetap sangat terbatas. Studi ini berargumen bahwa diperlukan model analisis sentimen yang diadaptasi secara kultural-linguistik untuk konteks UMKM Indonesia, yang dikembangkan melalui pendekatan Mixed-Method sequential exploratory. Pada fase kualitatif, Focus Group Discussion (FGD) digelar bersama 15 pelaku UMKM di Jawa Barat guna menggali kebutuhan dan konteks bisnis aktual. Fase kuantitatif lantas membangun model berbasis IndoBERT (indobenchmark/indobert-base-p1) yang di-fine-tune memakai 12.899 komentar media sosial dari empat platform: Instagram, TikTok, Facebook, dan Twitter. Tahap preprocessing memuat tiga elemen adaptasi kultural, kamus sentimen Islami, pemetaan emoji, serta normalisasi bahasa informal. Pada test set, model menorehkan akurasi 97% dengan weighted F1-score 0,97. Pada sisi kualitatif, ditemukan tiga tema dominan: Digital Paradox, logika Risk-Minimization, dan hambatan Human Capital di kalangan pelaku UMKM. Kontribusi penelitian ini terletak pada pipeline NLP teradaptasi budaya untuk bahasa Indonesia informal di media sosia.

Downloads

Download data is not yet available.

References

Kementerian Koperasi dan UKM Republik Indonesia, "Perkembangan Data Usaha Mikro, Kecil, Menengah (UMKM) dan Usaha Besar (UB)," Jakarta, 2023. [Online]. Available: https://www.kemenkopukm.go.id.

S. Kemp, "Digital 2024: Indonesia," DataReportal, Jan. 2024. [Online]. Available: https://datareportal.com/reports/digital-2024-indonesia

Kementerian Komunikasi dan Informatika RI, "Workshop UMKM Level Up: Kominfo Targetkan 30 Juta UMKM Adopsi Teknologi Digital pada 2024," Siaran Pers, Agustus 2024. [Online]. Available: https://menpan.go.id/site/berita-terkini/berita-daerah/kominfo-targetkan-30-juta-umkm-adopsi-teknologi-digital-pada-2024

B. Liu, “Sentiment Analysis and Opinion Mining,” Morgan & Claypool Publishers, 2012. doi: 10.2200/S00416ED1V01Y201204HLT016.

R. A. García-Hernández et al., “A Systematic Literature Review of Modalities, Trends, and Limitations in Emotion Recognition, Affective Computing, and Sentiment Analysis,” Aug. 01, 2024, Multidisciplinary Digital Publishing Institute (MDPI). doi: 10.3390/app14167165.

P. M. S. Ardinata, A. A. J. Permana, I. N. S. W. Wijaya, F. Teknik, and D. Kejuruan, “Identifikasi Dan Normalisasi Teks Slang Dengan Fasttext Pada Twitter Dalam Bahasa Indonesia,” Jurnal Pendidikan Teknologi dan Kejuruan, vol. 21, no. 1, 2024. doi: 10.23887/jptk-undiksha.v21i1.66381.

B. Wilie et al., "IndoNLU: Benchmark and Resources for Evaluating Indonesian Natural Language Understanding," in Proc. 1st Conf. Asia-Pacific Chapter of the Association for Computational Linguistics and 10th Int. Joint Conf. Natural Language Processing (AACL-IJCNLP), Suzhou, China, Dec. 2020, pp. 843–857, doi: 10.18653/v1/2020.aacl-main.85

F. Koto, A. Rahimi, J. H. Lau, and T. Baldwin, “IndoLEM and IndoBERT: A Benchmark Dataset and Pre-trained Language Model for Indonesian NLP,” Proc. 28th Int. Conf. Computational Linguistics, pp. 757–770, 2020, doi: 10.18653/v1/2020.coling-main.66.

N. Omrani, N. Rejeb, A. Maalaoui, M. Dabic, and S. Kraus, “Drivers of Digital Transformation in SMEs,” IEEE Trans. Eng. Manag., vol. 71, pp. 5030–5043, 2024, doi: 10.1109/TEM.2022.3215727.

A. S. Aribowo, H. Basiron, N. F. A. Yusof, and S. Khomsah, “Cross-domain sentiment analysis model on indonesian youtube comment,” International Journal of Advances in Intelligent Informatics, vol. 7, no. 1, pp. 12–25, 2021, doi: 10.26555/ijain.v7i1.554.

W. Christian, D. Adamlu, A. Yu, and D. Suhartono, “Leveraging IndoBERT and DistilBERT for Indonesian emotion classification in e-commerce reviews,” in Procedia Computer Science, Elsevier B.V., 2025, pp. 321–330. doi: 10.1016/j.procs.2025.08.284.

R. Purba, F. M. Sinaga, S. Jurnalis Pipin, and K. Kelvin, “Fine-Grained Sentiment Analysis On Big Data From Multi-Platform In Indonesia,” JITK (Jurnal Ilmu Pengetahuan dan Teknologi Komputer), vol. 11, no. 1, pp. 64–75, Aug. 2025, doi: 10.33480/jitk.v11i1.6549.

A. F. Setyawan and R. I. Nugraha, “Optimizing Gpt And Indobert For Sentiment Analysis And Consumer Trend Prediction On Lazada Product Reviews,” JIKO (Jurnal Informatika dan Komputer), vol. 8, no. 2, pp. 113–120, Jul. 2025, doi: 10.33387/jiko.v8i2.10066.

V. Braun and V. Clarke, “Using thematic analysis in psychology.,” Qual. Res. Psychol., vol. 3, no. 2, pp. 77–101, 2006, doi: 10.1191/1478088706qp063oa.

P. Robinson, “Designing and Conducting Mixed Methods Research,” Aust. N. Z. J. Public Health, vol. 31, no. 4, p. 388, Aug. 2007, doi: 10.1111/j.1753-6405.2007.00096.x.

J. Devlin, M.-W. Chang, K. Lee, K. T. Google, and A. I. Language, “BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding.” in Proc. 2019 Conf. North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT), Minneapolis, MN, USA, Jun. 2019, pp. 4171–4186, doi: 10.18653/v1/N19-1423.

H. Ahmadian, T. F. Abidin, H. Riza, and K. Muchtar, “Hybrid Models for Emotion Classification and Sentiment Analysis in Indonesian Language,” Applied Computational Intelligence and Soft Computing, vol. 2024, 2024, doi: 10.1155/2024/2826773.

H. Imaduddin, F. Yusfida A’la, and Y. S. Nugroho, “Sentiment Analysis in Indonesian Healthcare Applications using IndoBERT Approach.” IJACSA) International Journal of Advanced Computer Science and Applications, vol. 14, no. 8, 2023, doi: 10.14569/IJACSA.2023.0140813.

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,” Journal of Information Systems Engineering and Business Intelligence, vol. 11, no. 1, pp. 30–40, Feb. 2025, doi: 10.20473/jisebi.11.1.30-40.

G. V. Singh, S. Ghosh, M. Firdaus, A. Ekbal, and P. Bhattacharyya, “Predicting multi-label emojis, emotions, and sentiments in code-mixed texts using an emojifying sentiments framework,” Sci. Rep., vol. 14, no. 1, Dec. 2024, doi: 10.1038/s41598-024-58944-5.

Y. Lou, J. Zhou, J. Zhou, D. Ji, and Q. Zhang, “Emoji multimodal microblog sentiment analysis based on mutual attention mechanism,” Sci. Rep., vol. 14, no. 1, Dec. 2024, doi: 10.1038/s41598-024-80167-x.

Q. A. Xu, C. Jayne, and V. Chang, “An emoji feature-incorporated multi-view deep learning for explainable sentiment classification of social media reviews,” Technol. Forecast. Soc. Change, vol. 202, May 2024, doi: 10.1016/j.techfore.2024.123326.

J. Homepage, R. Rahman Salam, M. Fajri Jamil, and Y. Ibrahim, “MALCOM: Indonesian Journal of Machine Learning and Computer Science Sentiment Analysis of Cash Direct Assistance Distribution for Fuel Oil Using Support Vector Machine Analisis Sentimen Terhadap Bantuan Langsung Tunai (BLT) Bahan Bakar Minyak (BBM) Menggunakan Support Vector Machine,” vol. 3, pp. 27–35, 2023, doi: 10.57152/malcom.v3i1.590.

D. S. Nugroho, I. F. Hanif, M. A. Hasbi, F. Fredianto, A. M. Saputra, and R. Zildjian, “Analisis Sentimen Dugaan Pelanggaran Pemilu 2024 Berdasarkan Tweet Menggunakan Algoritma Naïve Bayes Classifier,” MALCOM: Indonesian Journal of Machine Learning and Computer Science, vol. 4, no. 3, pp. 1169–1176, Jul. 2024, doi: 10.57152/malcom.v4i3.1496.

I. G. B. A. Budaya and I. K. P. Suniantara, “Comparison of Sentiment Analysis Algorithms with SMOTE Oversampling and TF-IDF Implementation on Google Reviews for Public Health Centers,” MALCOM: Indonesian Journal of Machine Learning and Computer Science, vol. 4, no. 3, pp. 1077–1086, Jul. 2024, doi: 10.57152/malcom.v4i3.1459.

A. Librian, "Sastrawi: High Quality Stemmer Library for Indonesian Language (Bahasa)," GitHub Repository, 2014. [Online]. Available: https://github.com/sastrawi/sastrawi.

F. Koto dan G. Y. Rahmaningtyas, "InSet Lexicon: Evaluation of a Word List for Indonesian Sentiment Analysis in Microblogs," Proc. 2017 Int. Conf. Asian Language Processing (IALP), pp. 391–394, 2017, doi: 10.1109/IALP.2017.8300625.

J. Homepage et al., “MALCOM: Indonesian Journal of Machine Learning and Computer Science Sentiment Analysis of Online Lectures in Indonesia from Twitter Dataset Using InSet Lexicon Analisis Sentimen terhadap Perkuliahan Daring di Indonesia dari Twitter Dataset Menggunakan InSet Lexicon,” vol. 1, pp. 24–33, 2021, doi: 10.57152/malcom.v1i2.28.

J. R. Landis dan G. G. Koch, "The Measurement of Observer Agreement for Categorical Data," Biometrics, vol. 33, no. 1, pp. 159–174, 1977, doi: 10.2307/2529310.

T. Wolf et al., "Transformers: State-of-the-Art Natural Language Processing," Proc. 2020 Conf. Empirical Methods in Natural Language Processing: System Demonstrations, pp. 38–45, 2020, doi: 10.18653/v1/2020.emnlp-demos.6.

N. V Chawla, K. W. Bowyer, L. O. Hall, and W. P. Kegelmeyer, “SMOTE: Synthetic Minority Over-sampling Technique,” 2002, doi: 10.1613/jair.953.