Analisis Sentimen Ulasan Mobile Legends di Google Play Store dan YouTube Menggunakan Pelabelan Otomatis Roberta dan Klasifikasi Random Forest

Muhammad Rafid Pratama; Maya Rini Handayani; Wenty Dwi Yuniarti; Khothibul Umam

doi:10.30656/jsii.v12i2.10459

Authors

Muhammad Rafid Pratama UIN WALISONGO SEMARANG
Maya Rini Handayani UIN Walisongo Semarang
Wenty Dwi Yuniarti UIN Walisongo Semarang
Khothibul Umam UIN Walisongo Semarang

DOI:

https://doi.org/10.30656/jsii.v12i2.10459

Abstract

The rapid development of the mobile gaming industry has led to an increase in users and reviews for various popular titles, including Mobile Legends: Bang Bang. This research aims to analyze user perceptions of the Mobile Legends application through reviews obtained from Google Play Store and YouTube. The methods employed include data crawling, automatic labeling using the RoBERTa model for sentiment classification (positive, negative, and neutral), and modeling with the Random Forest algorithm. The dataset comprises 1,400 data points from Google Play Store and hundreds of data points from YouTube, all of which have undergone preprocessing. Model evaluation uses precision, recall, and f1-score metrics. The test results show that the model can classify reviews quite well, achieving an accuracy of 80% on Google Play Store data and 82% on YouTube data. The model demonstrates high performance in detecting negative and positive reviews, although the accuracy for the neutral class remains low. Overall, the Random Forest-based model is sufficiently reliable in processing user review data, providing insights into public perception of Mobile Legends across different platforms.

Keywords: Mobile Legends, Random Forest, Sentiment Analysis, Google Play Store, YouTube

References

[1] R. Andreas and D. Arymami, “Volume 8 Nomor 2 Tahun 2021 Hasrat Konsumsi Virtual dalam Permainan Daring Mobile legends: Perspektif Deleuze dan Guattari,” Jurnal Pemikiran Sosiologi , 2022.

[2] W. M. Haidar and E. R. Antika, “Prestasi Akademik Siswa Ditinjau Dari Kecanduan Bermain Game Online Mobile Legends,” TERAPUTIK: Jurnal Bimbingan dan Konseling, vol. 5, no. 3, pp. 319–325, Feb. 2022, doi: 10.26539/teraputik.53872.

[3] R. H. Nufus and U. Surapati, “Analisis Sentimen Persepsi Masyarakat Terhadap Timnas Indonesia U-23 dalam AFC-23 Asian Cup 2024 Pada Media Sosial X Menggunakan Metode Naïve Bayes Classifier,” Jurnal Indonesia : Manajemen Informatika dan Komunikasi, vol. 5, no. 3, pp. 2647–2657, Sep. 2024, doi: 10.35870/jimik.v5i3.964.

[4] J. Sirusstara, N. Alexander, A. Alfarisy, S. Achmad, and R. Sutoyo, “Clickbait Headline Detection in Indonesian News Sites using Robustly Optimized BERT Pre-training Approach (RoBERTa),” in 2022 3rd International Conference on Artificial Intelligence and Data Sciences (AiDAS), IEEE, Sep. 2022, pp. 1–6. doi: 10.1109/AiDAS56890.2022.9918678.

[5] Z. Sun, G. Wang, P. Li, H. Wang, M. Zhang, and X. Liang, “An improved random forest based on the classification accuracy and correlation measurement of decision trees,” Expert Syst Appl, vol. 237, p. 121549, Mar. 2024, doi: 10.1016/j.eswa.2023.121549.

[6] A. Prasetyo, T. Ridwan, and A. Voutama, “Analisis Sentimen Terhadap Aplikasi GBWHATSAPP Menggunakan Naive Bayes Classifier dan Random Forest Classifier,” JSiI (Jurnal Sistem Informasi), vol. 11, no. 1, pp. 1–9, Mar. 2024, doi: 10.30656/jsii.v11i1.6936.

[7] F. A. Larasati, D. E. Ratnawati, and B. T. Hanggara, “Analisis Sentimen Ulasan Aplikasi Dana dengan Metode Random Forest,” Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer, vol. 6, no. 9, pp. 4305–4313, 2022, [Online]. Available: http://j-ptiik.ub.ac.id

[8] M. Y. Aldean, P. Paradise, and N. A. Setya Nugraha, “Analisis Sentimen Masyarakat Terhadap Vaksinasi Covid-19 di Twitter Menggunakan Metode Random Forest Classifier (Studi Kasus: Vaksin Sinovac),” Journal of Informatics, Information System, Software Engineering and Applications (INISTA), vol. 4, no. 2, pp. 64–72, Jun. 2022, doi: 10.20895/inista.v4i2.575.

[9] T. Fadiyah Basar, D. E. Ratnawati, and I. Arwani, “Analisis Sentimen Pengguna Twitter terhadap Pembayaran Cashless menggunakan Shopeepay dengan Algoritma Random Forest,” Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer, vol. 6, no. 3, pp. 1426–1433, 2022, [Online]. Available: http://j-ptiik.ub.ac.id

[10] M. H. Aufan, M. R. Handayani, A. B. Nurjanna, N. Cahyo, H. Wibowo, and K. Umam, “The Perceptions of Semarang Five Star Hotel Tourists With Support Vector Machine on Google Reviews,” Jurnal Teknik Informatika (JUTIF), vol. x, No. y, pp. x-y, 2023, doi: 10.52436/jutif.

[11] R. M. Amir Latif, M. Talha Abdullah, S. U. Aslam Shah, M. Farhan, F. Ijaz, and A. Karim, “Data Scraping from Google Play Store and Visualization of its Content for Analytics,” in 2019 2nd International Conference on Computing, Mathematics and Engineering Technologies (iCoMET), IEEE, Jan. 2019, pp. 1–8. doi: 10.1109/ICOMET.2019.8673523.

[12] S. Alanazy and J. Tian, “Measuring API Usability and the Environment: A YouTube API Case Study,” 2025, pp. 176–186. doi: 10.1007/978-3-031-76273-4_14.