Analisis Sentimen Publik terkait Migrasi Tenaga Kerja Indonesia di Platform X menggunakan SVM-IndoBERT
Abstract
Diverse public opinions on social and economic issues related to labor migration are often expressed on the social media platform X (Twitter). This research aims to classify public sentiment toward this phenomenon by analyzing tweets containing the hashtag "#KaburAjaDulu". Sentiment classification is performed by comparing two Support Vector Machine (SVM) approaches that utilize indoBERT embeddings, a language model designed to capture the nuances of the Indonesian language. Both SVM models are trained using web crawling data from the X platform, with the main difference lying in the application of hyperparameter tuning on one of the models. The data collected through web crawling from the X platform then undergoes a pre-processing stage that includes text normalization and stopword removal. The results show that the SVM model optimized through hyperparameter tuning achieved an accuracy of 90.5%, higher than the SVM model without tuning which achieved only 77.7%. This finding underscores the importance of hyperparameter tuning in improving the performance of sentiment classification models, especially when utilizing rich feature representations such as indoBERT embeddings to understand deeper language context.
References
[2] H. Al Rochmanto, H. Brilianti and Azies, “Klasifikasi Opini Publik terhadap Kenaikan PPN 12% di Platform X menggunakan Multinomial Naïve Bayes,” Unisda J. Math. Comput. Sci., vol. 10, no. 2, pp. 57–66, 2024, [Online]. Available: https://e-jurnal.unisda.ac.id/index.php/ujmc/article/view/9120
[3] A. Amrullah, “Advanced Sentiment Analysis Using Deep Learning: A Comprehensive Framework for High-Accuracy and Interpretable Models,” Intellithings J., vol. 1, no. 1, pp. 21–31, 2025, [Online]. Available: https://e-jurnal.unisda.ac.id/index.php/intellithings/article/view/8972
[4] M. M. Henry, N. A. Hervanto, M. Isnan, D. Kurnianingrum, C. I. Ratnapuri, and B. Pardamean, “LLM2Vec Sentence Embeddings Analysis in Sentiment Classification,” in 2024 IEEE International Conference on Data and Software Engineering (ICoDSE), 2024, pp. 161–165. doi: 10.1109/ICoDSE63307.2024.10829901.
[5] C. T. Akpinar, Ö. Koşar, and A. Durdu, “Enhancing the Performance of Machine Learning Classification Models,” in 2025 24th International Symposium INFOTEH-JAHORINA (INFOTEH), 2025, pp. 1–6. doi: 10.1109/INFOTEH64129.2025.10959301.
[6] S. Saadah, Kaenova Mahendra Auditama, Ananda Affan Fattahila, Fendi Irfan Amorokhman, Annisa Aditsania, and Aniq Atiqi Rohmawati, “Implementation of BERT, IndoBERT, and CNN-LSTM in Classifying Public Opinion about COVID-19 Vaccine in Indonesia,” J. RESTI (Rekayasa Sist. dan Teknol. Informasi), vol. 6, no. 4, pp. 648–655, 2022, doi: 10.29207/resti.v6i4.4215.
[7] P. Refaeilzadeh, L. Tang, and H. Liu, “Cross-Validation,” in Encyclopedia of Database Systems, L. LIU and M. T. ÖZSU, Eds., Boston, MA: Springer US, 2009, pp. 532–538. doi: 10.1007/978-0-387-39940-9_565.
[8] C. Amanda, I. Jaya, and D. Arisandi, “Identification of Sexual Harassment in Social Media Comments Using IndoBERT and Support Vector Machine,” in 2024 8th International Conference on Electrical, Telecommunication and Computer Engineering (ELTICOM), 2024, pp. 42–45. doi: 10.1109/ELTICOM64085.2024.10864968.
[9] S. P. Andinny and E. B. Setiawan, “Sentiment Analysis on 2024 Regional Elections using Hybrid CNN-SVM with Semantic Features and Word2Vec,” in 2025 International Conference on Advancement in Data Science, E-learning and Information System (ICADEIS), 2025, pp. 1–7. doi: 10.1109/ICADEIS65852.2025.10933385.
[10] A. B. Y. A. Putra, Y. Sibaroni, and A. F. Ihsan, “Disinformation Detection on 2024 Indonesia Presidential Election using IndoBERT,” in 2023 International Conference on Data Science and Its Applications (ICoDSA), 2023, pp. 350–355. doi: 10.1109/ICoDSA58501.2023.10277572.
[11] D. S. Asudani, N. K. Nagwani, and P. Singh, “Impact of word embedding models on text analytics in deep learning environment: a review,” Artif. Intell. Rev., vol. 56, no. 9, pp. 10345–10425, 2023, doi: 10.1007/s10462-023-10419-1.
[12] L. B. Purbey and K. Lakhwani, “Aspect-based sentimental analysis using optimized multi-layered deep BiLSTM classifier,” Knowledge-Based Syst., vol. 324, p. 113832, 2025, doi: https://doi.org/10.1016/j.knosys.2025.113832.
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
Authors who publish in UJMC (Unisda Journal of Mathematics and Computer Science) agree to the following terms:
1.Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License (CC BY-SA 4.0) that allows others to share the work with an acknowledgment of the work's authorship and initial publication in this journal.
2.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.
3.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.
