Article Sidebar

Submitted
February 16, 2026
Accepted
May 7, 2026
Published
May 9, 2026
Download
PDF
Statistic
Read Counter : 0 Download : 0

Main Article Content

Abstract

Sexual harassment in online comment sections is a growing concern on social media platforms like TikTok, where informal language makes manual moderation ineffective. This study developed an automated detection model using a hybrid Indonesian bidirectional encoder representation from transformers (IndoBERT)-long short-term memory (LSTM) architecture, employing IndoBERT as a static feature extractor and an LSTM network to model sequential dependencies. Given the high-class imbalance in social media data, this study specifically evaluated the impact of the synthetic minority over-sampling technique (SMOTE) on classification performance. Experimental results showed that the base IndoBERT-LSTM model achieved a high overall accuracy of 89.04% but struggles with a low recall (0.40) for the minority harassment class. While applying SMOTE improved the model’s sensitivity (recall) for harassment to 0.54, it resulted in a significant decrease in precision, and an overall accuracy drop to 87.79%. These findings indicate that while oversampling can modestly enhance the detection of harassment instances, it introduces a substantial trade-off by increasing false positives. This study concludes that for highly informal and imbalanced TikTok data, standard oversampling techniques such as SMOTE may be less effective, suggesting the need for more advanced contextual augmentation or cost-sensitive learning approaches in future digital safety research.  

Keywords

Text Classification IndoBERT Embedding Long Short-Term Memory Sexual Harassment Comment SMOTE

Article Details

License

Authors who publish with this journal 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 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 (See The Effect of Open Access).
How to Cite
Mumtaz, N. L., Kesumawati, A., & Primandari, A. H. . (2026). Identification of Sexual Harassment Comment on Tiktok Platform Using Indobert Embedding and Long Short-Term Memory . Enthusiastic : International Journal of Applied Statistics and Data Science, 6(1), 82–94. https://doi.org/10.20885/enthusiastic.vol6.iss1.art8
Download Citation
Endnote/Zotero/Mendeley (RIS)
BibTeX
Crossref
Scopus
Google Scholar
Europe PMC

References

  1. A. Thompson, “Digital 2026 global overview report,” We Are Social Indonesia. Accessed: January 26, 2026. [Online]. Available: https://wearesocial.com/id/blog/2025/10/digital-2026-global-overview-report/
  2. S. Kemp, “Digital 2024 April global statshot report,” DataReportal – Global Digital Insights. Accessed: January 26, 2026. [Online]. Available: https://datareportal.com/reports/digital-2024-april-global-statshot
  3. V.L. Kumar and M.A. Goldstein, “Cyberbullying and adolescents,” Curr. Pediatr. Rep., vol. 8, no. 3, pp. 86–92, Sep. 2020, doi: 10.1007/s40124-020-00217-6.
  4. G.W. Giumetti and R.M. Kowalski, “Cyberbullying via social media and well-being,” Curr. Opin. Psychol., vol. 45, Jun. 2022, Art. no 101314, doi: 10.1016/j.copsyc.2022.101314.
  5. “SIMFONI-PPA.” Accessed: Jul. 04, 2025. [Online]. Available: https://kekerasan.kemenpppa.go.id/ringkasan
  6. World Bank, “KBGO World Bank Report,” 2023. [Online]. Available: https://documents.worldbank.org/en/publication/documents-reports/documentdetail
  7. /099637206212330304
  8. E.A. Vogels, “Online harassment occurs most often on social media, but strikes in other places, too,” Pew Research Center. Accessed: July 4, 2025. [Online]. Available: https://www.pewresearch.org
  9. /short-reads/2021/02/16/online-harassment-occurs-most-often-on-social-media-but-strikes-in-other-places-too/
  10. G.Z. Nabiilah, I.N. Alam, E.S. Purwanto, and M.F. Hidayat, “Indonesian multilabel classification using IndoBERT embedding and MBERT classification,” Int. J. Electr. Comput. Eng., vol. 14, no. 1, pp. 1071–1078, Feb. 2024, doi: 10.11591/ijece.v14i1.pp1071-1078.
  11. G.H. Setiawan, M.D.A. Pranata, I.B.A. Arimbawa, I.W.P. Giri, and N.P.L.C. Dayani, “Topic clustering of student complaints based on semantic meaning using the indoBERT and k-means models,” J. Appl. Inform. Comput., vol. 9, no. 4, pp. 1715–1721, Aug. 2025, doi: 10.30871/jaic.v9i4.10080.
  12. T.C. Praha, W. Widodo, and M. Nugraheni, “Indonesian fake news classification using transfer learning in CNN and LSTM,” JOIV, Int. J. Inform. Vis., vol. 8, no. 3, pp. 1213–1221, Sep. 2024, doi: 10.62527/joiv.8.3.2126.
  13. D.Y. Yefferson, V. Lawijaya, and A.S. Girsang, “Hybrid model: IndoBERT and long short-term memory for detecting Indonesian hoax news,” Int. J. Artif. Intell., vol. 13, no. 2, pp. 1913–1924, Jun. 2024, doi: 10.11591/ijai.v13.i2.pp1913-1924.
  14. L. Khan, A. Amjad, K.M. Afaq, and H.-T. Chang, “Deep sentiment analysis using CNN-LSTM architecture of English and Roman Urdu text shared in social media,” Appl. Sci., vol. 12, no. 5, Jan. 2022, Art. no 2694, doi: 10.3390/app12052694.
  15. A.H. Primandari and P. Ermayani, “An empirical studies on online gender-based violence: Classification analysis utilizing XGBOOST,” in AIP Conf. Proc. 3248, 2025, no. 1, Paper 040003, doi: 10.1063/5.0236703.
  16. V. Dogra et al., “A complete process of text classification system using state-of-the-art NLP models,” Comput. Intell. Neurosci., vol. 2022, 2022, Art. no 1883698, doi: 10.1155/2022/1883698.
  17. B. Wilie et al., “IndoNLU: Benchmark and resources for evaluating Indonesian natural language understanding,” in Proc. 1st Conf. Asia-Pac. Chapter Assoc. Comput. Ling. 10th Int. Joint Conf. Nat. Lang. Proc., s, 2020, pp. 843–857, doi: 10.18653/v1/2020.aacl-main.85.
  18. M.R. Farhan, A.A. Santoso, and J.J. Tedjasulaksana, “Sentiment analysis of public perception on freedom curriculum policy using text,” in 2025 Int. Conf. Inf. Technol. Res. Innov. (ICITRI), 2025, pp. 1–6, doi: 10.1109/ICITRI67507.2025.11232776.
  19. A. Vaswani et al., “Attention is all you need,” in Adv. Neural Inf. Process. Syst., 2017, pp. 1–11.
  20. N.V. Chawla, K.W. Bowyer, L.O. Hall, and W.P. Kegelmeyer, “SMOTE: Synthetic minority over-sampling technique,” J. Artif. Intell. Res., vol. 16, pp. 321–357, Jun. 2002, doi: 10.1613/jair.953.
  21. S.F. Taskiran, B. Turkoglu, E. Kaya, and T. Asuroglu, “A comprehensive evaluation of oversampling techniques for enhancing text classification performance,” Sci. Rep., vol. 15, Jul. 2025, Art. no. 21631, doi: 10.1038/s41598-025-05791-7.
  22. A. Khurana and O P. Verma, “Optimal feature selection for imbalanced text classification,” IEEE Trans. Artif. Intell., vol. 4, pp. 135–147, Feb. 2023, doi: 10.1109/TAI.2022.3144651.
  23. A. Kaur, K.S. Gill, R. Chauhan, and H.S. Pokhariya, “Harnessing LSTM networks for enhanced text classification: A comprehensive study,” in 2024 Int. Conf. Integr. Emerg. Technol. Digit. World (ICIETDW), 2024, pp. 1–5, doi: 10.1109/ICIETDW61607.2024.10939988.
  24. W.K. Sari, D.P. Rini, and R.F. Malik, “Text classification using long short-term memory,” in 2019 Int. Conf. Electr. Eng. Comput. Sci. (ICECOS), 2019, pp. 150–155. doi: 10.1109/ICECOS47637.2019.8984558.
  25. Hermansah, M. Muhajir, and P.C. Rodrigues, “Indonesian Inflation Forecasting with Recurrent Neural Network Long Short-Term Memory (RNN-LSTM),” Enthusiastic, Int. J. Appl. Stat. Data Sci., vol. 4, no. 2, pp. 132–142, Oct. 2024, doi: 10.20885/enthusiastic.vol4.iss2.art5.
No Related Submission Found