BERT Model Implementation for Dynamic Sentiment Analysis of Pertamina on Social Media X

Ronsen Purba; Rivaldi Lubis; Nadya Sikana; Gilbert Fernando Situmorang

doi:10.56741/IISTR.esl.001139

Authors

Ronsen Purba Universitas Mikroskil
Rivaldi Lubis
rivaldi.lubis@mikroskil.ac.id
Universitas Mikroskil
Nadya Sikana Universitas Mikroskil
Gilbert Fernando Situmorang Universitas Mikroskil

Keywords:

BERT, Dynamic Sentiment, Sentiment Analysis, Pertamina, Social Media

Abstract

This study aims to investigate the dynamics of public sentiment on platform X in response to the Pertamina corruption scandal, exploring how trust and perception shifted before and after the incident. Utilizing BERT-based sentiment classification model trained on real-world social media posts, the model achieved a validation loss of 0.5078 and an F1-score of 82.12%, demonstrating strong predictive performance for large-scale sentiment analysis. Results revealed a significant rise in negative sentiment and a decline in positive sentiment following the public disclosure of the scandal on February 25, 2025, reflecting a deep erosion of public trust in Pertamina. Qualitative thematic analysis further identified a shift from neutral or positive discussions focused on service quality and innovation to emotionally charged critiques emphasizing betrayal, distrust and institutional failure. These findings highlight the value of integrating deep learning classification with qualitative insights to monitor real-time public opinion and institutional reputation. The study underscores the critical need for transparency and effective communication strategies during reputational crises to rebuild public confidence. Limitations include the focus on a single social media platform, suggesting future research should incorporate cross-platform and multilingual analyses. Practically, this research offers actionable insights for corporate crisis management and contributes to understanding social media’s role in shaping public trust and accountability in the digital age.

Downloads

Download data is not yet available.

Author Biographies

Ronsen Purba, Universitas Mikroskil

Master of Information Technology, Informatics Faculty, Universitas Mikroskil

Rivaldi Lubis, Universitas Mikroskil

Information Technology, Informatics Faculty, Universitas Mikroskil

Nadya Sikana, Universitas Mikroskil

Information Technology, Informatics Faculty, Universitas Mikroskil

Gilbert Fernando Situmorang, Universitas Mikroskil

Computer Science, Informatics Faculty, Universitas Mikroskil

References

N. G. Alimin, “The role of social media in forming public opinion from a contemporary sociological perspective,” Jun. 2024, doi: 10.31235/osf.io/d7g89. DOI: https://doi.org/10.31235/osf.io/d7g89

Y. Hu, “Research on the application of social media data mining based on sentiment analysis,” Appl. Comput. Eng., vol. 121, no. 1, pp. 147–153, Jan. 2025, doi: 10.54254/2755-2721/2025.19843. DOI: https://doi.org/10.54254/2755-2721/2025.19843

M. A. A. Montaser et al., “Sentiment analysis of social media data: Business insights and consumer behavior trends in the USA,” Edelweiss Appl. Sci. Technol., vol. 9, no. 1, Jan. 2025, doi: 10.55214/25768484.v9i1.4164. DOI: https://doi.org/10.55214/25768484.v9i1.4164

Kompas, “Korupsi Pertamina rugikan negara Rp 193,7 triliun, bagaimana awal kasus ini?,” Feb. 2025. [Online]. Available: https://www.kompas.com/tren/read/2025/02/25/144500565/korupsi-pertamina-rugikan-negara-rp-193-7-triliun-bagaimana-awal-kasus-ini?page=all. [Eng. Trans.: Pertamina corruption costs the state Rp 193.7 trillion, how did this case begin?]

A. Kumar and K. R., “Real-time sentiment analysis system using the BERT model,” Int. J. Innov. Res. Comput. Commun. Eng., May 2024, doi: 10.15680/ijircce.2024.1205114. DOI: https://doi.org/10.15680/IJIRCCE.2024.1205114

S. Xiao, M. M. Alobaedy, S. B. Goyal, S. Singla, S. Kang, and R. Chadha, “Real-time sentiment analysis on social networks using meta-model and machine learning techniques,” Nov. 2023, doi: 10.12694/scpe.v24i4.2247. DOI: https://doi.org/10.12694/scpe.v24i4.2247

T. Dhar, S. Mishra, J. Menezes, N. Mishra, and A. Alkhayyat, “Exploring advanced techniques for sentiment analysis and emotion detection in social media networks,” in Proc. IEEE Int. Conf. Electron. Commun. (ICEC), Nov. 2024, pp. 1–4, doi: 10.1109/icec59683.2024.10837473. DOI: https://doi.org/10.1109/ICEC59683.2024.10837473

R. A. Fitrianto, A. S. Editya, M. M. Alamin, A. L. Pramana, and A. K. Alhaq, “Classification of Indonesian sarcasm tweets on X platform using deep learning,” in Proc. IEEE Int. Conf. Inf. Commun. Syst. (ICICOS), Jul. 2024, pp. 388–393, doi: 10.1109/icicos62600.2024.10636904. DOI: https://doi.org/10.1109/ICICoS62600.2024.10636904

A. Jazuli, W. Widowati, and R. Kusumaningrum, “Optimizing aspect-based sentiment analysis using BERT for comprehensive analysis of Indonesian student feedback,” Appl. Sci., vol. 15, no. 1, p. 172, Dec. 2024, doi: 10.3390/app15010172. DOI: https://doi.org/10.3390/app15010172

E. D. Madyatmadja et al., “Sentiment analysis on user reviews of Snapchat in Indonesia,” J. Comput. Sci., vol. 21, no. 1, pp. 158–167, Jan. 2025, doi: 10.3844/jcssp.2025.158.167. DOI: https://doi.org/10.3844/jcssp.2025.158.167

A. Nasution, H. Hijra, A. Fianda, N. Sianturi, and R. Rangkuti, “Code switching in naturalized Indonesian football player’s Instagram caption,” KLAUSA (Kajian Linguistik, Pembelajaran Bahasa, dan Sastra), vol. 8, pp. 24–33, Jul. 2024, doi: 10.33479/klausa.v8i2.1085. DOI: https://doi.org/10.33479/klausa.v8i2.1085

R. N. Muhammad, L. Wulandari S, and B. Tanggahma, “Pengaruh media sosial pada persepsi publik terhadap sistem peradilan: Analisis sentimen di Twitter,” vol. 7, no. 1, 2024, doi: 10.31933/unesrev.v7i1. [Eng. Trans.: The influence of social media on public perception of the judicial system: Sentiment analysis on Twitter]

N. C. A. Prasetyo and A. N. Rahmanto, “Analisis jaringan dinamis informasi dan sentimen berita ekonomi studi kasus pada Detik dan CNBC Indonesia (Dynamic network analysis of economic news information and sentiment: Case study on Detik and CNBC Indonesia),” 2024. [Eng. Trans.: Dynamic network analysis of economic news information and sentiment: Case study on Detik and CNBC Indonesia]

Z. Liu, J. Wu, C. Y. H. Wu, and X. Xia, “Shifting sentiments: Analyzing public reaction to COVID-19 containment policies in Wuhan and Shanghai through Weibo data,” Humanit. Soc. Sci. Commun., vol. 11, no. 1, Aug. 2024, doi: 10.1057/s41599-024-03592-3. DOI: https://doi.org/10.1057/s41599-024-03592-3

H. Indrayani, R. Nurlita, and T. Kharisma, Eds., Dinamika dan strategi humas pemerintah di Indonesia. Jakarta, Indonesia: Iprahumas Indonesia, 2021. [Eng. Trans.: Dynamics and strategies of government public relations in Indonesia]

L. R. Pandiangan and I. L. Wijayakusuma, “Analisis sentimen para kandidat Pilpres 2024 dengan model bahasa BERT,” E-Jurnal Matematika, vol. 13, no. 4, p. 253, Nov. 2024, doi: 10.24843/mtk.2024.v13.i04.p470. [Eng. Trans.: Sentiment analysis of the 2024 presidential candidates using the BERT language model] DOI: https://doi.org/10.24843/MTK.2024.v13.i04.p470

D. F. Putra and Y. Sibaroni, “Sentiment analysis for the 2024 presidential election (Pilpres) using BERT CNN,” Eduvest, vol. 4, no. 11, pp. 11042–11056, Nov. 2024, doi: 10.59188/eduvest.v4i11.49961. DOI: https://doi.org/10.59188/eduvest.v4i11.49961

J. Cohen, “A coefficient of agreement for nominal scales,” Educ. Psychol. Meas., vol. 20, no. 1, pp. 37–46, 1960, doi: 10.1177/001316446002000104. DOI: https://doi.org/10.1177/001316446002000104

B. Więckowska, K. B. Kubiak, P. Jóźwiak, W. Moryson, and B. Stawińska-Witoszyńska, “Cohen’s kappa coefficient as a measure to assess classification improvement following the addition of a new marker to a regression model,” Int. J. Environ. Res. Public Health, vol. 19, no. 16, 2022, doi: 10.3390/ijerph191610213. DOI: https://doi.org/10.3390/ijerph191610213

D. Laufer and W. T. Coombs, “How should a company respond to a product harm crisis? The role of corporate reputation and consumer-based cues,” Bus. Horiz., vol. 49, no. 5, pp. 379–385, 2006, doi: 10.1016/j.bushor.2006.01.002. DOI: https://doi.org/10.1016/j.bushor.2006.01.002

P. H. Kim, D. L. Ferrin, C. D. Cooper, and K. T. Dirks, “Removing the shadow of suspicion: The effects of apology versus denial for repairing competence- versus integrity-based trust violations,” J. Appl. Psychol., vol. 89, no. 1, pp. 104–118, 2004, doi: 10.1037/0021-9010.89.1.104. DOI: https://doi.org/10.1037/0021-9010.89.1.104

P. Burnap, R. Gibson, L. Sloan, R. Southern, and M. Williams, “140 characters to victory?: Using Twitter to predict the UK 2015 General Election,” Elect. Stud., vol. 41, pp. 230–233, 2016, doi: 10.1016/j.electstud.2015.11.017. DOI: https://doi.org/10.1016/j.electstud.2015.11.017

E. F. Yatnih, “Pengaruh media sosial terhadap persepsi dan penegakan hukum pidana: Dampak media sosial terhadap opini publik, proses hukum dan keadilan pidana,” Equality Before The Law, vol. 4, no. 2, Oct. 2024, doi: 10.36232/equalitybeforethelaw.v4i2.451. [Eng. Trans.: The influence of social media on perception and criminal law enforcement: The impact of social media on public opinion, legal process, and criminal justice] DOI: https://doi.org/10.36232/equalitybeforethelaw.v4i2.451