Klasifikasi Sentimen Review Pengguna pada Platform Steam Menggunakan Arsitektur Transformer DistilBERT

Dody Pradipta; Eko Widodo; David Fahmi A; M. Iqbal Izzul  Haq

doi:10.31004/riggs.v5i2.11000

Authors

Dody Pradipta Politeknik Elektronika Negeri Surabaya
Eko Widodo Universitas Islam Kadiri
David Fahmi A Politeknik Elektronika Negeri Surabaya
M. Iqbal Izzul Haq Politeknik Elektronika Negeri Surabaya

DOI:

https://doi.org/10.31004/riggs.v5i2.11000

Keywords:

Analisis Sentimen, Steam, DistilBERT, Deep Learning, Natural Language Processing

Abstract

Ulasan pengguna pada platform Steam mengandung informasi penting yang dapat digunakan untuk mengetahui persepsi pemain terhadap suatu game. Namun, jumlah ulasan yang besar menyebabkan proses analisis secara manual menjadi kurang efisien. Penelitian ini bertujuan untuk melakukan klasifikasi sentimen ulasan pengguna Steam menggunakan model berbasis Deep Learning, yaitu DistilBERT. Metode penelitian yang digunakan adalah eksperimen dengan pendekatan kuantitatif dan mengadopsi framework CRISP-DM. Dataset yang digunakan terdiri dari 17.495 ulasan pengguna yang dibagi menjadi data latih sebesar 80% dan data uji sebesar 20%. Proses analisis meliputi data preparation, tokenisasi menggunakan DistilBERT Tokenizer, fine-tuning model DistilBERT, serta evaluasi menggunakan metrik accuracy, precision, recall, dan F1-score. Hasil pengujian menunjukkan bahwa model DistilBERT mampu menghasilkan nilai akurasi sebesar 90%, dengan nilai precision sebesar 90%, recall sebesar 89%, dan F1-score sebesar 90%. Hasil tersebut menunjukkan bahwa DistilBERT memiliki kemampuan yang baik dalam memahami konteks teks dan melakukan klasifikasi sentimen secara efektif. Meskipun demikian, model masih mengalami kesulitan dalam menangani ulasan yang mengandung sentimen campuran, ironi, dan bahasa informal.

Downloads

Download data is not yet available.

References

[1] Newzoo, “Newzoo’s Global Games Market Report 2024,” Newzoo.

[2] Valve Corporation, “Steam Year in Review 2024,” Valve Corporation.

[3] A. Amrullah, “Sentiment Analysis in the Age of Transformers and Large Language Models: A Comprehensive Review of Recent Advances and Future,” 2025. [Online]. Available: https://doi.org/xxxxxxxxx

[4] I. Perikos and A. Diamantopoulos, “Explainable Aspect-Based Sentiment Analysis Using Transformer Models,” Big Data and Cognitive Computing, vol. 8, no. 11, p. 141, Oct. 2024, doi: 10.3390/bdcc8110141.

[5] S. Tzimiris, S. Nikiforos, M. N. Nikiforos, D. Mouratidis, and K. L. Kermanidis, “A Comparative Evaluation of Transformer-Based Language Models for Topic-Based Sentiment Analysis,” Electronics (Basel)., vol. 14, no. 15, p. 2957, Jul. 2025, doi: 10.3390/electronics14152957.

[6] R. F. Reza, Muhmmad Thoriq, and Rd. Imam Saepul Millah, “Sentiment Analysis of Marketplace Review with Islamic Perspective using Fine-Tuning DistilBERT,” Khazanah Journal of Religion and Technology, vol. 2, no. 2, pp. 45–54, Jan. 2025, doi: 10.15575/kjrt.v2i2.1118.

[7] A. Aljabar, B. M. Karomah, N. Tarisafitri, and J. Jeffry, “Sentiment Analysis in Indonesian’s Presidential Election 2024 Using Transfomer (Distilbert-Base-Uncased),” Journal of System and Computer Engineering (JSCE), vol. 6, no. 2, pp. 197–203, Apr. 2025, doi: 10.61628/jsce.v6i2.1867.

[8] J. N. Gandhi, K. V. Guru, A. R. Kannan, R. A. Sudhan, S. A. Kumar, and M. Bharathvaj, “Efficient Sentiment Classification using DistilBERT for Enhanced NLP Performance,” 2025, pp. 1500–1511. doi: 10.2991/978-94-6463-718-2_125.

[9] A. Jazuli, Widowati, and R. Kusumaningrum, “Optimizing Aspect-Based Sentiment Analysis Using BERT for Comprehensive Analysis of Indonesian Student Feedback,” Applied Sciences, vol. 15, no. 1, p. 172, Dec. 2024, doi: 10.3390/app15010172.

[10] Wes McKinney, Python for Data Analysis, 3rd ed. O’Reilly Media, 2022.

[11] I. Goodfellow, Y. Bengio, and A. Courville, Deep Learning. 2016.

[12] A. Paszke et al., “PyTorch: An Imperative Style, High-Performance Deep Learning Library,” 2019.

[13] J. Devlin, M.-W. Chang, K. Lee, K. T. Google, and A. I. Language, “BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding.” [Online]. Available: https://github.com/tensorflow/tensor2tensor

[14] S. Ruder, “An overview of gradient descent optimization algorithms,” Jun. 2017, [Online]. Available: http://arxiv.org/abs/1609.04747

[15] T. Hastie, R. Tibshirani, and J. Friedman, The Elements of Statistical Learning, 2nd ed. Springer, 2009.

[16] D. M. W. Powers and Ailab, “EVALUATION: FROM PRECISION, RECALL AND F-MEASURE TO ROC, INFORMEDNESS, MARKEDNESS & CORRELATION.”