Klasifikasi Komentar Judol pada Media Sosial dengan Menggunakan Metode Recurrent Neural Network dan Long Short-Term Memory

Ilham Saputra; Anita Qoiriah

doi:10.61132/merkurius.v4i2.1565

Authors

Ilham Saputra Universitas Negeri Surabaya
Anita Qoiriah Universitas Negeri Surabaya

DOI:

https://doi.org/10.61132/merkurius.v4i2.1565

Keywords:

Hybrid RNN-LSTM, Long Short-Term Memory, Online Gambling, Recurrent Neural Network, Text Classification

Abstract

The proliferation of online gambling promotional comments on Indonesian social media has become a serious issue requiring fast and accurate automated handling. This study aims to implement a Hybrid Recurrent Neural Network (RNN) and Long Short-Term Memory (LSTM) method to classify online gambling comments and compare its performance with standalone RNN and LSTM models. The research utilized a dataset of 10,230 comments subjected to comprehensive preprocessing stages, including the normalization of non-standard language using a slang dictionary. Testing was conducted across three data-splitting scenarios: 90:10, 80:20, and 70:30. Experimental results demonstrate that the standalone LSTM model achieved the highest average accuracy of 97.45%. However, the Hybrid RNN–LSTM model showed significant superiority in terms of performance stability, yielding the lowest standard deviation (0.0027) and the smallest Coefficient of Variation (0.28%) across all scenarios. These findings indicate that while the LSTM architecture is highly effective at capturing short-text context, the Hybrid approach provides better robustness against fluctuations in data proportions, making it highly relevant for implementation as an automated detection system on social media.

References

Aji, H. B., & Setiawan, E. B. (2023). Detecting Hoax Content on Social Media Using Bi-LSTM and RNN. BITS, 5(1), 114–125. https://doi.org/10.47065/bits.v5i1.3585

Akbar, G. G., Ulumudin, A., Kania, I., & Nurliawati, N. (2024). Policy brief: Tackling the social, economic, and. 3(4), 1017–1035.

Astari, Y., & Rozaqi, S. W. (2021). Analisis sentimen multi-class pada sosial media menggunakan metode LSTM. 4(1), 8–12.

Chuluq, K., & Nudin, S. R. (2024). Klasifikasi cyberbullying pada media sosial menggunakan RNN dan LSTM. 6(19), 501–509.

Fahrudin, A., Satispi, E., Subardhini, M., Hartini, R., Andayani, R., & Jayaputra, A. (2024). Online gambling addiction: Problems and solutions for policymakers and stakeholders in Indonesia. 8(11), 1–17.

Hochreiter, S., & Schmidhuber, J. (1997). Long Short-Term Memory. Neural Computation, 9(8), 1735–1780. https://doi.org/10.1162/neco.1997.9.8.1735

Humaniora, P. D., Bawembang, N., & Umboh, J. (2024). Enforcement of the ITE Law and the impact of online gambling promotion. 8(2), 2268–2279. https://doi.org/10.36526/js.v3i2

Julianti, O. N., Suarna, N., & Prihartono, W. (2024). Penerapan NLP pada analisis sentimen judi online di media sosial Twitter. 8(3), 2936–2941.

Lee, J., Rajtmajer, S., Srivatsavaya, E., & Wilson, S. (2023). Online Self-Disclosure, Social Support, and User Engagement During the COVID-19 Pandemic. Trans. Soc. Comput., 6(3–4). https://doi.org/10.1145/3617654

Mahjouby, M. E. L., Fahssi, K. El, Bennani, M. T., & Lamrini, M. (2025). Simple RNN-LSTM hybrid deep learning model for forecasting. TELKOMNIKA, 23(1), 175–184. https://doi.org/10.12928/TELKOMNIKA.v23i1.25925

Parfenova, A. (2023). Risk prediction of pathological gambling in social media.

Qiu, C. (2024). Classification of comments on social media based on LSTM. 124–128. https://doi.org/10.54254/2755-2721/54/20241432

Sari, T. I., Ardilla, Z. N., Hayatin, N., & Maskat, R. (2022). Abusive comment identification on Indonesian social media data using hybrid deep learning. IJAI, 11(3), 895–904. https://doi.org/10.11591/ijai.v11.i3.pp895-904

Waluyo, I. G. (2023). Sentiment analysis of negative comments on social media using LSTM with TensorFlow. 2(7), 1015–1030.

Zahra, A. (2023). Hoax identification on social media using RNN and LSTM. 448–451.

Zhang, W., Huang, G., Wang, G., & Wang, Y. (2019). Prediction high frequency parameters based on neural network. https://doi.org/10.1088/1757-899X/631/5/052035