Utilizing IndoBERT and BERTopic to Explore Public Opinion on BPS Instagram Posts
DOI:
https://doi.org/10.30871/jaic.v9i5.10327Keywords:
Sentiment Analysis, IndoBERT, BERTopic, Social Media, Central Statistics Agency, Public OpinionAbstract
This study aims to analyze public sentiment and topics of opinion toward the Central Statistics Agency (BPS) through comments on the Instagram account @bps_statistics. A total of 3,075 comments collected from January 1 to July 24, 2025, were analyzed using the IndoBERT model for sentiment classification and BERTopic for topic modeling. The IndoBERT model was developed using a semi-supervised learning approach, achieving an 88% classification accuracy with high precision and recall across all sentiment categories. The analysis results show that neutral comments dominate (52.78%), followed by negative comments (31.54%) and positive comments (15.69%). Topic modeling on negative sentiment revealed two main issues: distrust of poverty data and preference for international institution indicators such as the World Bank. Positive sentiment reflects appreciation for the quality of statistical data and moral support for BPS. Neutral comments mostly contain informative discussions about socioeconomic conditions and access to digital services. These findings emphasize the importance of improving BPS public communication, particularly in bridging the gap in public perception of official data. The social media-based approach has proven effective as a complement to formal surveys in capturing public opinion in a broad and dynamic manner.
Downloads
References
[1] Badan Pusat Statistik, Peraturan Kepala BPS Nomor 117 Tahun 2023 tentang Quality Gates. BPS RI, 2023.
[2] Badan Pusat Statistik, Analisis hasil Survei Kebutuhan Data (Vol. 16). BPS RI, 2024.
[3] S. Stieglitz, M. Mirbabaie, B. Ross, and C. Neuberger, “Social media analytics–Challenges in topic discovery, data collection, and data preparation,” Int. J. Inf. Manage., vol. 39, pp. 156–168, 2018, doi: 10.1016/j.ijinfomgt.2017.12.002.
[4] M. Harahap, F. Firman, and R. Ahmad, “Penggunaan social media dan perubahan sosial budaya masyarakat,” Edukatif: J. Ilmu Pendidik., vol. 3, no. 1, pp. 135–143, 2021, doi: 10.31004/edukatif.v3i1.252.
[5] W. Kencana, "Peran dan manfaat komunikasi pembangunan pada aplikasi pelacak covid-19 sebagai media komunikasi kesehatan", Commed : Jurnal Komunikasi Dan Media, vol. 5, no. 1, p. 83-95, 2020. https://doi.org/10.33884/commed.v5i1.2495
[6] A. S. Nabiilah and D. R. Rahman, “Classification of Indonesia false news detection using IndoBERT and syntactic features,” Procedia Comput. Sci., vol. 219, pp. 433–439, 2023, doi: 10.1016/j.procs.2023.01.189.
[7] M. Amanda and R. Nurmawati, “Analisis sentimen dan pemodelan topik opini publik terhadap Badan Pusat Statistik melalui media sosial Twitter,” J. Teknol. Sist. Komput., vol. 11, no. 2, pp. 98–106, 2023.
[8] K. A. Simanjuntak, M. Koyimatu, and Y. P. Ervanisari, “Analisis perubahan opini publik terhadap kendaraan listrik di Indonesia melalui komentar YouTube: Pendekatan topic modeling BERTopic,” J. Inov. Kewirausahaan, vol. 1, no. 3, pp. 1–12, 2024, doi: 10.37817/jurnalinovasikewirausahaan.v1i3.
[9] R. Adriansah and I. Santoso, “Analisis sentimen Badan Pusat Statistik berdasarkan media online,” in Seminar Nasional Official Statistics 2019: Pengembangan Official Statistics dalam mendukung Implementasi SDG’s, 2019, pp. 217–225.
[10] J. W. Campbell, “Public participation and trust in government: Results from a vignette experiment,” J. Policy Stud., vol. 38, no. 2, pp. 23–31, 2023, doi: 10.52372/jps38203.
[11] M. Grootendorst, “BERTopic: Neural topic modeling with a class-based TF-IDF procedure,” arXiv preprint arXiv:2203.05794, 2022. [Online]. Available: https://arxiv.org/abs/2203.05794
[12] O. Martínez-Cámara, M. T. Martín-Valdivia, L. A. Ureña-López, and A. Montejo-Ráez, “Evaluating the effectiveness of text pre-processing in sentiment analysis,” Appl. Sci., vol. 12, no. 17, Art. no. 8765, 2022, doi: 10.3390/app12178765.
[13] B. Wilie et al., “IndoNLU: Benchmark and resources for evaluating Indonesian natural language understanding,” in Proc. 1st Conf. Asia-Pacific Chapter Assoc. Comput. Linguistics and 10th Int. Joint Conf. Natural Lang. Process., 2020, pp. 843–857. [Online]. Available: https://aclanthology.org/2020.aacl-main.84B.
[14] M. Khodeir and A. Elghannam, “Efficient topic identification for urgent MOOC forum posts using BERTopic and traditional topic modeling techniques,” Educ. Inf. Technol., 2024, doi: 10.1007/s10639-024-13003-4.
[15] D. Maier, A. Waldherr, and M. Eismann, “A topic modeling comparison between LDA, NMF, Top2Vec, and BERTopic to support social science research,” Front. Sociol., vol. 7, Art. no. 886498, 2022, doi: 10.3389/fsoc.2022.886498.
[16] S. D. Simbolon, R. N. Syah, and H. Hartono, “A sentiment analysis and topic modelling of the socio-economic registration 2022,” in Proc. Int. Conf. Data Sci. Official Stat. (ICDSOS), 2023. [Online]. Available: https://proceedings.stis.ac.id/icdsos/article/view/301
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2025 Ahmad Farhan Anugrah, Rendy Dwi Agatha
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).
