Sentiment and Topic Analysis of Public Opinion on Indonesia’s Minister of Finance Using IndoBERTweet, TF-IDF, and Latent Dirichlet Allocation
DOI:
https://doi.org/10.21512/emacsjournal.v8i1.15346Keywords:
X, Sentiment Analysis, IndoBERTweet, Topic Modelling, Temporal Trend Analysis, Ministry of FinanceAbstract
In today’s technology-based society, people share their opinions on online social media platforms, which can be used as data for sentiment analysis. One of the most popular platforms for obtaining publicly accessible data is X. This study analyzes public views of the Ministry of Finance (MoF) by examining 9,543 tweets gathered from February to September 2025. The data collected was preprocessed through cleaning, name entities grouping, and keywords filtering, then evaluated using IndoBERTweet, and keywords were extracted using the Term Frequency-Inverse Document Frequency (TF-IDF). For topic modelling, Latent Dirichlet Allocation (LDA) was used, and sentiment distributions were tracked over time through temporal aggregation. To obtain more specific public opinion sentiment analysis, a neutral classification was added to differentiate from the previous studies that used only positive and negative classifications. To support this approach, a pre-trained model with three sentiment classifications was used. The results show that neutral sentiment dominated the tweets followed by negative sentiment then positive sentiment, especially during the transition to the new Ministry of Finance, showing the relevance of real-world events to online public opinion on X. Based on topic trends, public opinion shows the trend change from fiscal policy and leadership to criticism and leadership change.
References
Ahmadian, H., Abidin, T. F., Riza, H., & Muchtar, K. (2023). Transformer-Based Indonesian Language Model for Emotion Classification and Sentiment Analysis. 2023 International Conference on Information Technology and Computing (ICITCOM), (pp. 209-214). Yogyakarta, Indonesia.
Ardiyanto, M. (2024). Aardiiiiy/indobertweet-base-Indonesian-sentiment-analysis. (Hugging Face) Retrieved September 2025, from https://huggingface.co/Aardiiiiy/indobertweet-base-Indonesian-sentiment-analysis
Damayanti, N. M., Ariningtyas, I. D., Icham, M. I., & Sari, A. P. (2025). ANALISIS SENTIMEN PUBLIK PADA TAGAR #BTSCOMEBACK DI PLATFORM X MENGGUNAKAN INDOBERTWEET . JITET (Jurnal Informatika dan Teknik Elektro Terapan), 13(3), 1142-1153.
Firdaus, R., Asror, I., & Herdiani, A. (2021). Lexicon-Based Sentiment Analysis of Indonesian Language Student Feedback Evaluation. Ind. Journal on Computing, 6(1), 1-12.
Khairul, I., Mutawalli, L., Bagye, W., & Tantoni, A. (2025). Automated Label Extraction for Sentiment Analysis in Indonesian Text. International Journal on Advanced Science, Engineering and Information Technology, 718-728.
Lin, C.-H., & Nuha, U. (2023). Sentiment analysis of Indonesian datasets based on a hybrid deep-learning strategy. Journal of Big Data.
Mailo, F. F., & Lazuardi, L. (2019). Analisis Sentimen Data Twitter Menggunakan Metode Text Mining Tentang Masalah Obesitas di Indonesia. Journal of Information Systems for Public Health, 4(1), 28-36.
Qi, Y., & Shabrina, Z. (2023). Sentiment analysis using Twitter data: a comparative application of lexicon- and machine-learning-based approach. Social Network Analysis and Mining.
Rizkia, A. S., Wufron, W., & Roji, F. F. (2025). Analisis Sentimen Coretax: Perbandingan Pelabelan Data Manual, Transformers-Based, dan Lexicon-Based pada Performa IndoBERT . MALCOM: Indonesian Journal of Machine Learning and Computer Science, 5(3), 1037-1048.
Romadhony, A., Faraby, S. A., Rismala, R., Wisesti, U. N., & Arifianto, A. (2024). Sentiment Analysis on a Large Indonesian Product Review Dataset. Journal of Information Systems Engineering and Business Intelligence.
Satria, H. (2023, July). Crawl Data Twitter Menggunakan Tweet Harvest - Juli 2023. Retrieved September 2025, from https://helmisatria.com/blog/crawl-data-twitter-menggunakan-tweet-harvest/
Sayarizki, P., Hasmawati, & Nurrahmi, H. (2024). Implementation of IndoBERT for Sentiment Analysis of Indonesian Presidential Candidates. Indonesian Journal on Computing (Indo-JC), 61-72.
Sejati, P. T., Alzami, F., Marjuni, A., Indrayani, H., & Puspitarini, I. D. (2024). Aspect-Based Sentiment Analysis for Enhanced Understanding of 'Kemenkeu' Tweets. Journal of Applied Informatics and Computing, 487-498.
Setiawan, B. (2024). A Review of Sentiment Analysis Applications in Indonesia Between 2023-2024. Journal Information Engineering and Educational Technology.
Setiawan, V. D., Iswavigra, D. U., & Anggiratih, E. (2025). Implementation of IndoBERT for Sentiment Analysis of the Constitutional Court's Decision Regarding the Minimum Age of Vice Presidential Candidates. Scientific Journal of Informatics, 397-406.
Zhang, P., Harris, R. D., & Zheng, J. (2025). GNN-based social media sentiment analysis for stock market forecasting. Expert Systems With Applications, 291.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2026 Surya Sujarwo, Jeklin Harefa, Alexander Alexander
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 - Share Alike 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.
USER RIGHTS
All articles published Open Access will be immediately and permanently free for everyone to read and download. We are continuously working with our author communities to select the best choice of license options, currently being defined for this journal as follows: Creative Commons Attribution-Share Alike (CC BY-SA)
