Implementasi Fine-Tuning BERT untuk Analisis Sentimen terhadap Review Aplikasi PUBG Mobile di Google Play Store

Alex Sander P. Braja, Achmad Kodar

Abstract


Game online adalah salah satu hal yang paling relevan untuk beradaptasi dengan teknologi internet. PUBG Mobile adalah salah satu game online terpopuler di Indonesia, telah diunduh lebih dari 500 juta kali dengan 41,8 juta ulasan pengguna pada tahun 2022 di Google Play. Ulasan pengguna memainkan peran penting dalam keberhasilan pengembangan aplikasi. Ulasan pengguna berupa teks dalam format data tidak terstruktur yang menimbulkan kerumitan saat bekerja dengan analisis sentimen. Ada sebuah pendekatan baru yang disebut BERT. BERT Ini model transfer-learning  memperkenalkan model pre-training yang diperlukan untuk lebih baik dalam representasi konteks tekstual. Penelitian ini menguji kinerja BERT untuk analisis sentimen menggunakan dua model pre-training. Kami menggunakan model pre-training IndoBERTBASE dan BERTBASE Multilingual. Data yang digunakan adalah ulasan pengguna untuk aplikasi PUBG Mobile di Google Play Store. Kami juga melakukan pengaturan hyperparameter untuk menemukan model pencarian yang optimal menggunakan dua pendekatan pelabelan data: pelabelan berbasis skor dan pelabelan berbasis TextBlob untuk menentukan efisiensi model. Hasil percobaan menunjukkan bahwa model fine-tuned IndoBERT memiliki akurasi yang lebih baik dalam pelabelan data berbasis Textblob dengan akurasi tertinggi 94 % pada learning rate 0.00002, batch size 32, jumlah epoch 5, dan waktu pelatihan 12 menit.

Keywords


Game Online; Analisis sentimen; BERT; PUBG Mobile

Full Text:

PDF (Indonesian)

References


Biasramadhan Pandu, “Indonesia Gaming Market: A Window Opportunity for Chinese Developers,” www.cekindo.com, 2021. https://www.cekindo.com/blog/indonesia-gaming-market (accessed Dec. 16, 2022).

All Correct Games, “The Indonesian Gaming Market | Allcorrect Games,” allcorrectgames.com, 2022. https://allcorrectgames.com/insights/indonesia/ (accessed Dec. 16, 2022).

M. A. Andrhasa, “Prediksi Esports 2022: Menuju Puncak Gemilang Esports Indonesia?,” nawalakarsa.id, 2022. https://nawalakarsa.id/game-teknologi/prediksi-esports-2022/ (accessed Dec. 16, 2022).

R. da Silva, J. de Oliveira Liberato Magalhães, I. R. Rodrigues Silva, R. Fagundes, E. Lima, and A. Maciel, “Rating Prediction of Google Play Store apps with application of data mining techniques,” IEEE Lat. Am. Trans., vol. 19, no. 01, pp. 26–32, 2021, doi: 10.1109/TLA.2021.9423823.

E. Noei and K. Lyons, “A study of gender in user reviews on the Google Play Store,” Empir. Softw. Eng., vol. 27, no. 2, p. 34, 2021, doi: 10.1007/s10664-021-10080-8.

Z. Gao, A. Feng, X. Song, and X. Wu, “Target-dependent sentiment classification with BERT,” IEEE Access, vol. 7, pp. 154290–154299, 2019, doi: 10.1109/ACCESS.2019.2946594.

L. Yang, Y. Li, J. Wang, and R. S. Sherratt, “Sentiment Analysis for E-Commerce Product Reviews in Chinese Based on Sentiment Lexicon and Deep Learning,” IEEE Access, vol. 8, pp. 23522–23530, 2020, doi: 10.1109/ACCESS.2020.2969854.

Pristiyono, M. Ritonga, M. A. Al Ihsan, A. Anjar, and F. H. Rambe, “Sentiment analysis of COVID-19 vaccine in Indonesia using Naïve Bayes Algorithm,” IOP Conf. Ser. Mater. Sci. Eng., vol. 1088, no. 1, p. 12045, Feb. 2021, doi: 10.1088/1757-899X/1088/1/012045.

A. M. Rahat, A. Kahir, and A. K. M. Masum, “Comparison of Naive Bayes and SVM Algorithm based on Sentiment Analysis Using Review Dataset,” in 2019 8th International Conference System Modeling and Advancement in Research Trends (SMART), 2019, pp. 266–270. doi: 10.1109/SMART46866.2019.9117512.

J. Devlin, M. W. Chang, K. Lee, and K. Toutanova, “BERT: Pre-training of deep bidirectional transformers for language understanding,” NAACL HLT 2019 - 2019 Conf. North Am. Chapter Assoc. Comput. Linguist. Hum. Lang. Technol. - Proc. Conf., vol. 1, no. Mlm, pp. 4171–4186, 2019.

S. González-Carvajal and E. C. Garrido-Merchán, “Comparing BERT against traditional machine learning text classification,” May 2020, [Online]. Available: http://arxiv.org/abs/2005.13012

C. A. Putri, “Analisis Sentimen Review Film Berbahasa Inggris Dengan Pendekatan Bidirectional Encoder Representations from Transformers,” JATISI (Jurnal Tek. Inform. dan Sist. Informasi), vol. 6, no. 2, pp. 181–193, 2020, doi: 10.35957/jatisi.v6i2.206.

C. Sun, X. Qiu, Y. Xu, and X. Huang, “How to Fine-Tune BERT for Text Classification?,” in Chinese Computational Linguistics, 2019, pp. 194–206.

Q. T. Nguyen, T. L. Nguyen, N. H. Luong, and Q. H. Ngo, “Fine-Tuning BERT for Sentiment Analysis of Vietnamese Reviews,” in 2020 7th NAFOSTED Conference on Information and Computer Science (NICS), 2020, pp. 302–307. doi: 10.1109/NICS51282.2020.9335899.

B. Wilie et al., “IndoNLU: Benchmark and Resources for Evaluating Indonesian Natural Language Understanding.” arXiv, 2020. doi: 10.48550/ARXIV.2009.05387.

C. G. Skarpathiotaki and K. E. Psannis, “Cross-Industry Process Standardization for Text Analytics,” Big Data Res., vol. 27, p. 100274, 2022, doi: https://doi.org/10.1016/j.bdr.2021.100274.

M. Singh, A. K. Jakhar, and S. Pandey, “Sentiment analysis on the impact of coronavirus in social life using the BERT model,” Soc. Netw. Anal. Min., vol. 11, no. 1, p. 33, 2021, doi: 10.1007/s13278-021-00737-z.

S. El Anigri, M. M. Himmi, and A. Mahmoudi, “How BERT’s Dropout Fine-Tuning Affects Text Classification?,” in Business Intelligence, 2021, pp. 130–139.

R. Qasim, W. H. Bangyal, M. A. Alqarni, and A. Ali Almazroi, “A Fine-Tuned BERT-Based Transfer Learning Approach for Text Classification,” J. Healthc. Eng., vol. 2022, p. 3498123, 2022, doi: 10.1155/2022/3498123.




DOI: http://dx.doi.org/10.51213/jimp.v7i3.779

Copyright (c) 2023 Alex Sander P. Braja, Achmad Kodar

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