Issue

Vol. 11, No. 2, May 2026 (Article in Progress)

Creative Commons License

This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.

Evaluating Synonym Augmentation Impact on SBERT Performance for Indonesian Social Media Style Classification

https://doi.org/10.22219/kinetik.v11i2.2580
Jessicha Putrianingsih Pamput
Universitas Negeri Makassar
Aindri Rizky Muthmainnah
Universitas Negeri Makassar
Dewi Fatmarani Surianto
Universitas Negeri Makassar
Nur Azizah Eka Budiarti
Universitas Negeri Makassar
Abdul Wahid
Universitas Negeri Makassar

Corresponding Author(s) : Dewi Fatmarani Surianto

dewifatmaranis@unm.ac.id

Kinetik: Game Technology, Information System, Computer Network, Computing, Electronics, and Control, Vol. 11, No. 2, May 2026 (Article in Progress)

Abstract

Language on social media reflected the identity and characteristics of its users, including differences in language style between generations. Millennials and Generation Z were two dominant demographic groups in digital communication that exhibited linguistic variations, which often caused gaps in understanding during online interactions. Variations in language structure and expression posed challenges in understanding the context of cross-generational communication. Therefore, this study aimed to classify linguistic styles across generations in social media texts by combining Sentence-BERT (SBERT). FastText-based synonym augmentation in Indonesian, and Support Vector Machine (SVM) as a margin-based classification model that utilizes embedding representations from SBERT. The results showed that synonym augmentation improved model accuracy from 85% to 93%, with a similarity threshold of 0.7 providing the best balance between data diversity and semantic consistency. These findings confirmed that synonym-based augmentation and SBERT semantic adaptation were effective in capturing generational linguistic differences in informal Indonesian. This approach had the potential to be applied in other NLP tasks that required contextual understanding of social language variation, such as sentiment analysis and cross-generational dialect detection.

Keywords

FastText Generation SBERT Social Media Synonym Augmentation
Pamput, J. P., Muthmainnah, A. R., Surianto, D. F., Budiarti, N. A. E., & Wahid, A. (2026). Evaluating Synonym Augmentation Impact on SBERT Performance for Indonesian Social Media Style Classification. Kinetik: Game Technology, Information System, Computer Network, Computing, Electronics, and Control, 11(2). https://doi.org/10.22219/kinetik.v11i2.2580
Download Citation
Endnote/Zotero/Mendeley (RIS)
BibTeX
References
  1. D. Ci. A. Ginting, S. G. Rezeki, A. A. Siregar, and Nurbaiti, “Analisis Pengaruh Jejaring Sosial Terhadap Interaksi Sosial di Era Digital,” PPIMAN: Pusat Publikasi Ilmu Manajemen, vol. 2, no. 1, pp. 22–29, 2024, doi: https://doi.org/10.59603/ppiman.v2i1.280.
  2. C. Li, G. Ning, Y. Xia, K. Guo, and Q. Liu, “Does the Internet Bring People Closer Together or Further Apart? The Impact of Internet Usage on Interpersonal Communications,” Behavioral Sciences, vol. 12, no. 11, p. 425, Oct. 2022, doi: 10.3390/bs12110425.
  3. Z. R. Eslami, T. Larina, and R. Pashmforoosh, “Identity, Politeness and Discursive Practices in a Changing World,” Russian Journal of Linguistics, vol. 27, no. 1, pp. 7–38, 2023, doi: 10.22363/2687-0088-34051.
  4. A. Gondra, “Linguistic Variability across Four Generations of Basque Spanish Speakers,” Journal of Language Contact, vol. 16, no. 4, pp. 429–455, 2023, doi: 10.1163/19552629-01604001.
  5. G. Šakytė-Statnickė, L. Budrytė-Ausiejienė, I. Luka, and V. Drozdova, “Internal and External Communication between Employees of Different Generations: Emerging Problems in Lithuanian, Latvian, and Swedish Tourism Organizations,” 2023, Center for International Scientific Research of VSO and VSPP. doi: 10.29036/jots.v14i26.427.
  6. S. R. Febriani and A. W. Ritonga, “The Perception of Millennial Generation on Religious Moderation through Social Media in the Digital Era,” Millah: Journal of Religious Studies, pp. 313–334, May 2022, doi: 10.20885/millah.vol21.iss2.art1.
  7. K. A. Boyle, “Millennial Career-identities: Reevaluating Social Identification and Intergenerational Relations,” J. Intergener. Relatsh., vol. 21, no. 1, pp. 89–109, 2023, doi: 10.1080/15350770.2021.1945989.
  8. M. Ridlo, Y. Satriyadi, A. H. Nasution, and N. A. Arandri, “Analisis Pengaruh Bahasa Gaul di Kalangan Mahasiswa Terhadap Bahasa Indonesia di Zaman Sekarang,” Jurnal Kewarganegaraan, vol. 5, no. 2, pp. 561–569, Dec. 2021, doi: 10.31316/jk.v5i2.1940.
  9. N. Tarihoran, E. Fachriyah, Tressyalina, and I. R. Sumirat, “The Impact of Social Media on the Use of Code Mixing by Generation Z,” International Journal of Interactive Mobile Technologies, vol. 16, no. 7, pp. 54–69, 2022, doi: 10.3991/ijim.v16i07.27659.
  10. L. Taber, S. Dominguez, and S. Whittaker, “Ignore the Affordances; It’s the Social Norms: How Millennials and Gen-Z Think About Where to Make a Post on Social Media,” Proc. ACM Hum. Comput. Interact., vol. 7, no. CSCW2, pp. 1–26, Sep. 2023, doi: 10.1145/3610102.
  11. M. D. K. Putri, B. M. K. Widarso, D. A. F. ROsanti, K. A. P. Alifariani, H. Maulana, and D. P. Arum, “Evolusi Kosa Kata Gaul Studi Antara Generasi Z Dan Milenial,” Jurnal Pustaka Cendekia Pendidikan, vol. 2, no. 2, pp. 147–153, 2024, doi: https://doi.org/10.70292/jpcp.v2i2.80.
  12. V. Sardila, N. Faiza, Nuraini, and N. Ainiyah, “Analisis Perbedaan Bahasa Melayu Riau Klasik dan Bahasa Melayu Riau Modern di Kampar,” Gurindam: Jurnal Bahasa dan Sastra, vol. 4, no. 1, pp. 18–26, 2024.
  13. Q. Fitrie, S. Tisnasari, and A. Supena, “Analisis Kontrastif Afiksasi Verba Bahasa Jawa Dialek Banten Dan Bahasa Indonesia Dalam Kanal Youtube Guyonan Pegandikan Periode 2021,” BAHTERA INDONESIA: Jurnal Penelitian Pendidikan Bahasa dan Sastra Indonesia, vol. 8, no. 2, pp. 401–413, 2023, doi: https://bahteraindonesia.unwir.ac.id/index.php/BI/article/view/428.
  14. M. Olivia et al., “Analisis Perbedaan Verba Dialek Sikka Natar dan Dialek Tana Ai Dalam Bahasa Sikka,” Journal Scientific of Mandalika (JSM), vol. 3, no. 10, 2022, [Online]. Available: http://ojs.cahayamandalika.com/index.php/jomla/issue/archive
  15. W. D. Suryono, E. Utami, and D. Ariatmanto, “Analisa Perbandingan Stemming Dokumen Teks Berbahasa Jawa dengan Algoritma Levenshtein Distance Dan Jaro-Winkler,” JIPI (Jurnal Ilmiah Penelitian dan Pembelajaran Informatika), vol. 10, no. 1, pp. 774–780, Jan. 2025, doi: 10.29100/jipi.v10i1.6092.
  16. Y. Khiong, “Analisis Perbandingan Pola Kalimat Bahasa Mandarin dengan Bahasa Indonesia,” PARAMASASTRA, vol. 8, no. 2, pp. 180–186, 2021, [Online]. Available: http://journal.unesa.ac.id/index.php/paramasastra
  17. E. Erwina, “Analisis Perbedaan Makna Dasar Kata Dalam Bahasa Indonesia dan Bahasa Malaysia,” SAWERIGADING, vol. 27, no. 1, pp. 117–125, 2021.
  18. F. El-Alami, S. Ouatik El Alaoui, and N. En Nahnahi, “Contextual Semantic Embeddings Based in Fine-Tuned Arabert Model for Arabic Text Multi-Class Categorization,” Journal of King Saud University - Computer and Information Sciences, vol. 34, no. 10, pp. 8422–8428, Nov. 2022, doi: 10.1016/j.jksuci.2021.02.005.
  19. H. Fouadi, H. El Moubtahij, H. Lamtougui, and A. Yahyaouy, “BERT-Based Models for Classifying Multi-Dialect Arabic Texts,” IAES International Journal of Artificial Intelligence (IJ-AI), vol. 13, no. 3, p. 3437, Sep. 2024, doi: 10.11591/ijai.v13.i3.pp3437-3446.
  20. R. Silva Barbon and A. T. Akabane, “Towards Transfer Learning Techniques—BERT, DistilBERT, BERTimbau, and DistilBERTimbau for Automatic Text Classification from Different Languages: A Case Study,” Sensors, vol. 22, no. 21, Nov. 2022, doi: 10.3390/s22218184.
  21. A. Bello, S. C. Ng, and M. F. Leung, “A BERT Framework to Sentiment Analysis of Tweets,” Sensors, vol. 23, no. 1, p. 506, Jan. 2023, doi: 10.3390/s23010506.
  22. H. Saleh et al., “Advancing Arabic Dialect Detection with Hybrid Stacked Transformer Models,” Front. Hum. Neurosci., vol. 19, 2025, doi: 10.3389/fnhum.2025.1498297.
  23. N. J. Prottasha et al., “Transfer Learning for Sentiment Analysis Using BERT Based Supervised Fine-Tuning,” Sensors, vol. 22, no. 11, Jun. 2022, doi: 10.3390/s22114157.
  24. D. Ariyus, D. Manongga, and I. Sembiring, “Enhancing Sentiment Analysis of Indonesian Tourism Video Content Commentary on TikTok: A FastText and Bi-LSTM Approach,” Engineering, Technology & Applied Science Research, vol. 14, no. 6, pp. 18020–18028, Dec. 2024, doi: 10.48084/etasr.8859.
  25. H. Thamrin, D. Oktafiani, I. I. Rasyid, and I. M. Fauzi, “Classification of SWOT Statements Employing BERT Pre-Trained Model Embedding,” Jurnal Sistem Informasi Bisnis, vol. 14, no. 2, pp. 143–152, Apr. 2024, doi: 10.21456/vol14iss2pp143-152.
  26. M. Roman, A. Shahid, M. I. Uddin, Q. Hua, and S. Maqsood, “Exploiting Contextual Word Embedding of Authorship and Title of Articles for Discovering Citation Intent Classification,” Complexity, vol. 2021, 2021, doi: 10.1155/2021/5554874.
  27. F. Yuni Dharta, X. Guilin, Y. Karliena, M. Butarbutar, and E. Diantoro, “Multigenerational Workforce Management Strategy in the Digital Era,” Journal Markcount Finance, vol. 2, no. 2, 2024, doi: 10.70177/jmf.v2i2.1285.
  28. N. Madrueño, A. Fernández-Isabel, M. Cuesta, C. Lancho, G. Polo Vera, and I. Martín de Diego, “Novel utterance data augmentation for intent classification using large language models,” Neural Comput. Appl., vol. 37, no. 32, pp. 26711–26736, Nov. 2025, doi: 10.1007/s00521-025-11642-3.
  29. H. Q. Abonizio, E. C. Paraiso, and S. Barbon, “Toward Text Data Augmentation for Sentiment Analysis,” IEEE Transactions on Artificial Intelligence, vol. 3, no. 5, pp. 657–668, Oct. 2022, doi: 10.1109/TAI.2021.3114390.
  30. H. Dai et al., “AugGPT: Leveraging ChatGPT for Text Data Augmentation,” IEEE Trans. Big Data, vol. 11, no. 3, pp. 907–918, Jun. 2025, doi: 10.1109/TBDATA.2025.3536934.
  31. M. Rusydi, A. Akbar, M. Vebryanti, F. N. Tsani, and H. Z. Zavira, “Analisis Perbedaan Penggunaan Gaya Bahasa Antara Generasi Milenial dan Generasi Z dalam Komunikasi Online : Studi Kasus Akun X @xcintakiehlx dan @nnauraayu,” Jurnal Pendidikan Tambusai, vol. 8, no. 2, pp. 27167–27175, 2024.
  32. A. Molenaar, D. Lukose, L. Brennan, E. L. Jenkins, and T. A. McCaffrey, “Using Natural Language Processing to Explore Social Media Opinions on Food Security: Sentiment Analysis and Topic Modeling Study,” J. Med. Internet Res., vol. 26, p. e47826, Mar. 2024, doi: 10.2196/47826.
  33. E. Chersoni, E. Santus, C. R. Huang, and A. Lenci, “Decoding word embeddings with brain-based semantic features,” Computational Linguistics, vol. 47, no. 3, pp. 663–698, Oct. 2021, doi: 10.1162/COLI_a_00412.
  34. S. Yagi, A. Elnagar, and S. Fareh, “A benchmark for evaluating Arabic word embedding models,” Nat. Lang. Eng., vol. 29, no. 4, pp. 978–1003, Jul. 2023, doi: 10.1017/S1351324922000444.
  35. Alfa Santoso Budiwidjojo Putra, “Membangun Sinergi Lintas Generasi: Strategi Kolaboratif untuk Meningkatkan Kinerja Organisasi di Era Digital,” PaKMas: Jurnal Pengabdian Kepada Masyarakat, vol. 4, no. 2, pp. 429–436, Nov. 2024, doi: 10.54259/pakmas.v4i2.3129.
  36. R. Choudhary, Y. A. Shaik, P. Yadav, and A. Rashid, “Generational Differences in Technology Behavior: A systematic Literature Review,” Journal of Infrastructure, Policy and Development, vol. 8, no. 9, p. 6755, Sep. 2024, doi: 10.24294/jipd.v8i9.6755.
  37. J. C. Lapendy, A. Aulia, C. Resky, A. Tenriola, D. F. Surianto, and U. S. Sidin, “Optimizing Sentiment Analysis of Electric Vehicles Through Oversampling Techniques on Youtube Comments,” JANAPATI, vol. 14, no. 1, pp. 169–182, 2025, doi: 10.23887/janapati.v14i1.88205.
  38. H. M. Alawadh, A. Alabrah, T. Meraj, and H. T. Rauf, “Attention-Enriched Mini-BERT Fake News Analyzer Using the Arabic Language,” Future Internet, vol. 15, no. 2, Feb. 2023, doi: 10.3390/fi15020044.
  39. W. Wulandari et al., “Semantic Feature Engineering with LSA-SVM for Cyberbullying Comment Classification on Instagram,” Informatica, vol. 49, no. 15, Mar. 2025, doi: 10.31449/inf.v49i15.6992.
  40. A. Mardiah, S. Dillah, D. F. Surianto, N. Fadilah, and S. G. Zain, “Classification of Livin’ by Mandiri Customer Satisfaction Using MLP with BM25 and TF-IDF Feature Weighting,” Kinetik: Game Technology, Information System, Computer Network, Computing, Electronics, and Control, vol. 10, no. 3, Jun. 2025, doi: 10.22219/kinetik.v10i3.2248.
  41. N. Fujishiro, Y. Otaki, and S. Kawachi, “Accuracy of the Sentence-BERT Semantic Search System for a Japanese Database of Closed Medical Malpractice Claims,” Applied Sciences (Switzerland), vol. 13, no. 6, Mar. 2023, doi: 10.3390/app13064051.
  42. O. Alharbi, “A Deep Learning Approach Combining CNN and Bi-LSTM with SVM Classifier for Arabic Sentiment Analysis,” International Journal of Advanced Computer Science and Applications, vol. 12, no. 6, pp. 165–172, 2021, doi: 10.14569/IJACSA.2021.0120618.
  43. Y. Wiciaputra, J. Young, and A. Rusli, “Bilingual Text Classification in English and Indonesian via Transfer Learning using XLM-RoBERTa,” International Journal of Advances in Soft Computing and its Applications, vol. 13, no. 3, pp. 73–87, Dec. 2021, doi: 10.15849/IJASCA.211128.06.
  44. N. Ahmed, A. L. C. Barczak, M. A. Rashid, and T. Susnjak, “Runtime Prediction of Big Data Jobs: Performance Comparison of Machine Learning Algorithms and Analytical Models,” J. Big Data, vol. 9, no. 1, Dec. 2022, doi: 10.1186/s40537-022-00623-1.
  45. Z. Nassr, F. Benabbou, N. Sael, and T. Hamim, “Improving Sentiment Analysis Performance on Imbalanced Moroccan Dialect Datasets Using Resample and Feature Extraction Techniques,” Information (Switzerland), vol. 16, no. 1, Jan. 2025, doi: 10.3390/info16010039.
Read More
Author biographies is not available.
Download this PDF file
Statistic
Read Counter : 54

Downloads

Download data is not yet available.