Analyzing the #KaburDuluAja Phenomenon as an Indicator of Brain Drain in Indonesia: A Hybrid Text Mining Approach
DOI:
https://doi.org/10.32493/JJSDM.v9i2.59252Keywords:
Association Rule Mining; Brain Drain; Clustering; Hybrid; #KaburDuluAja; Sosial MediaAbstract
In recent years, an increasing number of Indonesian youth have expressed a desire to seek better opportunities and life prospects abroad. One of the hashtags widely used to articulate this aspiration is #KaburDuluAja. This hashtag has emerged as an expression of emotions, anxiety, and even frustration among certain segments of society, particularly the younger generation, in response to the current social, economic, and political conditions in Indonesia. This study aims to comprehensively examine the phenomenon of public discourse on social media related to the #KaburDuluAja hashtag as a reflection of the potential for brain drain in Indonesia. To achieve this objective, a hybrid approach is employed, integrating Clustering, Association Rule Mining, and Sentiment Classification methods. The research adopts a quantitative approach supported by text mining techniques and social media data analysis. Furthermore, this study is both descriptive and predictive in nature. The research does not focus on a specific geographical location; rather, it examines public conversations on social media platforms, particularly Twitter (currently known as X). The data utilized in this study were collected through a web crawling process. The findings indicate that public conversations related to the #KaburDuluAja phenomenon can be categorized into five main clusters. The evaluation of several classification models reveals that the Naïve Bayes algorithm achieves the highest accuracy in predicting sentiment, reaching 99.85%. The K-Nearest Neighbor (KNN) model achieves an accuracy of 75.79%, while the Decision Tree and Random Forest models demonstrate relatively lower performance, with accuracy levels around 60%. The #KaburDuluAja phenomenon is not merely a form of humor or casual expression on social media; rather, it represents a genuine reflection of social unrest, particularly concerning employment opportunities, welfare conditions, and the future prospects of Indonesia’s younger generation.
References
[1] Beine, M., Docquier, F., & Rapoport, H. (2022). Brain drain and human capital formation in developing countries: Winners and losers. The Economic Journal, 132(646), 1903–1940. https://doi.org/10.1093/ej/ueac010
[2] Carling, J., & Collins, F. (2018). Aspiration, desire and drivers of migration. Journal of Ethnic and Migration Studies, 44(6), 909–926. https://doi.org/10.1080/1369183X.2017.1384134
[3] Czaika, M., & Reinprecht, C. (2022). Migration drivers in a digital age: Understanding aspirations and capabilities. Journal of Ethnic and Migration Studies, 48(12), 2835–2852. https://doi.org/10.1080/1369183X.2021.1986267
[4] Hanny, D., & Resch, B. (2024). Clustering-based joint topic-sentiment modeling of social media data: A neural networks approach. Information (Switzerland), 15(4), 200.
[5] Hill, C., Irshadiat, F., Johnson, M., & Fresneda, J. (2025). An analytical assessment of sentiment analysis trends and methods through systematic review and topic modeling. Decision Analytics Journal, 17. doi:https://doi.org/10.1016/j.dajour.2025.100644
[6] Ibanez, M. R., Ventura, A. C., Mateos, F. C., & Jimenez, P. M. (2023). A review on sentiment analysis from social media platforms . Expert Systems With Applications , 223.
[7] International Labour Organization. (2022). World employment and social outlook: Trends 2022. Geneva: ILO.
[8] Lowin, M. (2024). A Text-Based Predictive Maintenance Approach for Facility Management Requests Utilizing Association Rule Mining and Large Language Models. machine learning and knowledge extraction, 6, 233-258. doi:https://do.org/10.3390/make6010013
[9] Nguyen, T. T., Mullaputi, P. S., Yue, X., Mane, H., Santhos, A., Dennard, E., . . . Nguyen, Q. C. (2026). A decade of discourse: Exploring sentiments and trends around immigration on social media from 2014 to 2024. Social Science and Medicine.
[10] Nip, J. Y., & Berthelier, B. (2024). Social media sentiment analysis. In Encyclopedia (Vol. 4, pp. 1590–1598). doi:https://doi.org/10.3390/encyclopedia4040104
[11] Oller, J. S., & Spadavecchia, C. (2024). Migration and emotions in the media: can socioeconomic indicators predict emotions in images associated with immigrants? Journal of Computational Social Science, 963-994.
[12] Pavaloaia, V. D. (2024). Clustering algorithms in sentiment analysis techniques in social media. International Journal of Advanced Computer Science and Applications, 15(3), 123–130.
[13] Rasianto, R., & Sutedi, S. (2023). Association rule mining using FP-growth algorithm for pattern discovery in textual data.
[14] Regina, E. Sutinah, and N. Agustina, “Clustering Kualitas Kinerja Karyawan Pada Perusahaan Bahan Kimia Menggunakan Algoritma K-Means,” J. Media Inform. Budidarma, vol. 5, no. 2, p. 573, 2021, doi: 10.30865/mib.v5i2.2909.
[15] Rogers, R. (2021). Digital methods for social science research. SAGE Publications.
[16] Sabna, E., Mustika, B., Fonda, H., Irfan, D., Hang, S., & Pekanbaru, T. (2020). Text Mining Menggunakan Algoritma K-Means Clustering Untuk Memprediksi Keinginan Pasar Terkait Perjalanan Wisata Text Mining Uses K-Means Clustering Algorithm To Predict Market Desires for Tourism Travel. Journal of Information Technology and Computer Science (INTECOMS), 3(2), 380–386.
[17] Saputra, A., et al. (2023). Application of k-means clustering, association rule mining, and classification algorithms in text mining analysis.
[18] Sugiyono. (2020). Metode penelitian kuantitatif, kualitatif, dan R&D. Bandung: Alfabeta.
[19] tim CNN. (2025). Survei #KaburAjaDulu: Mayoritas Gen Z Ingin Pindah ke Luar Negeri. CNN Indonesia. Retrieved March 09, 2025, from https://www.cnnindonesia.com/gaya-hidup/20250309155529-277-1206753/survei-kaburajadulu-mayoritas-gen-z-ingin-pindah-ke-luar-negeri#:~:text=Survei%20%23KaburAjaDulu:%20Mayoritas%20Gen%20Z%20Ingin%20Pindah%20ke%20Luar%20Negeri
[20] Vicari, S., & Murru, M. F. (2020). One platform, a thousand worlds: On Twitter irony in the Catalan independence debate. New Media & Society, 22(5), 797–818. https://doi.org/10.1177/1461444819879132
[21] World Bank. (2019). Migration and development brief 31. Washington, DC: World Bank. Retrieved from Migration and development brief 31.
[22] Zhang, X. (2023). Text classification algorithms exploration on sentiment analysis. Applied and Computational Engineering, 5, 99-103.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2026 Ulfa Meilinda Putri, Hendro Margono
This work is licensed under a Creative Commons Attribution 4.0 International License.
Authors who publish in this journal agree to the following terms:
The author owns the copyright of the article and assigns to the journal the right of first publication with the work simultaneously licensed under the terms Atribusi 4.0 Internasional (CC BY 4.0)
which allows others to share the work with acknowledgment of the work's authorship and initial publication in this journal.Authors may enter into separate additional contractual arrangements for the non-exclusive distribution of the published journal version of the work (for example, posting it to an institutional repository or publishing it in a book), with acknowledgment of the work's original publication in this journal.
Authors are permitted and encouraged to post their work online (for example, in institutional repositories or on their websites) before and during the submission process, as this can lead to productive exchanges, as well as earlier and larger citations of published work (See The Effect of Open Access).
.png)
