ANALISIS SENTIMEN BERBASIS TOPIK ULASAN PENGGUNA APLIKASI ROBLOX MENGGUNAKAN INTEGRASI LDA DAN SVM
Abstract
Perkembangan platform permainan virtual komunal seperti Roblox diiringi oleh tingginya volume ulasan pengguna di Google Play Store. Ulasan tersebut mengandung informasi penting mengenai kepuasan pengguna dan berbagai kendala teknis, namun jumlahnya yang besar menyulitkan proses evaluasi secara manual. Penelitian ini bertujuan menganalisis opini pengguna melalui pendekatan analisis sentimen berbasis topik menggunakan metodologi Knowledge Discovery in Databases (KDD). Dataset sebanyak 40.089 ulasan berbahasa Indonesia dianalisis menggunakan Latent Dirichlet Allocation (LDA) untuk mengekstraksi topik utama dan Support Vector Machine (SVM) untuk mengklasifikasikan polaritas sentimen. Ketidakseimbangan kelas sentimen diatasi melalui penerapan penyesuaian bobot kelas (class weight) pada proses pelatihan model SVM. Hasil pemodelan LDA mengidentifikasi empat topik utama dengan nilai Coherence Score sebesar 0,5547 dan Perplexity 191,5, yaitu masalah akun dan gangguan teknis, pengalaman bermain dan interaksi sosial, fitur item serta monetisasi, serta performa aplikasi dan koneksi jaringan. Model SVM memberikan performa terbaik pada pembagian data 70:30 dengan akurasi 85,22%, presisi 89%, recall 85%, dan F1-score 86%. Hasil penelitian menunjukkan bahwa integrasi LDA dan SVM efektif dalam mengungkap pola opini pengguna dan dapat menjadi dasar bagi pengembang dalam memprioritaskan perbaikan aplikasi.
Downloads
References
T. Fajriah and E. R. Ningsih, “Pengaruh Teknologi Komunikasi Terhadap Interaksi Sosial di Era Digital,” Merdeka Indonesia Journal International4, vol. 4, no. 1, Jun. 2024.
Y. Liu, H. Duan, and W. Cai, “User-Generated Content and Editors in Games: A Comprehensive Survey,” IEEE Transaction On Games, Jul. 2024, [Online]. Available: http://arxiv.org/abs/2412.13743
Y. Kou and X. Gui, “Harmful Design in the Metaverse and How to Mitigate it: A Case Study of User-Generated Virtual Worlds on Roblox,” Association for Computing Machinery (ACM), Jul. 2023, pp. 175–188. doi: 10.1145/3563657.3595960.
Y. joo Kang, U. jun Lee, and S. Lee, “Who Makes Popular Content? Information Cues from Content Creators for Users’ game Choice: Focusing on User-Created Content Platform ‘Roblox,’” Entertain. Comput., vol. 50, p. 100697, May 2024, doi: 10.1016/J.ENTCOM.2024.100697.
Roblox Corporation, “Roblox Reports Fourth Quarter and Full Year 2024 Financial Results,” Roblox Corporation – Investor Relations. Accessed: Nov. 10, 2025. [Online]. Available: https://ir.roblox.com/news/news-details/2025/Roblox-Reports-Fourth-Quarter-and-Full-Year-2024-Financial-Results/default.aspx
T. Liu et al., “RoseMatcher: Identifying the impact of user reviews on app updates,” Inf. Softw. Technol., vol. 161, p. 107261, Sep. 2023, doi: 10.1016/J.INFSOF.2023.107261.
G. Brauwers and F. Frasincar, “A Survey on Aspect-Based Sentiment Classification,” ACM Comput. Surv., vol. 55, no. 4, Apr. 2023, doi: 10.1145/3503044.
W. Zhang, X. Li, Y. Deng, L. Bing, and W. Lam, “A Survey on Aspect-Based Sentiment Analysis: Tasks, Methods, and Challenges,” IEEE Trans. on Knowl. and Data Eng., vol. 35, no. 11, pp. 11019–11038, Nov. 2023, doi: 10.1109/TKDE.2022.3230975.
E. Erniyati, P. Harsani, M. Mulyati, and L. D. Fahriza, “Topic Modeling LDA and SVM in Sentiment Analysis of Hotel Reviews,” Komputasi: Jurnal Ilmiah Ilmu Komputer dan Matematika, vol. 20, no. 2, pp. 93–100, Jul. 2023, doi: 10.33751/komputasi.v20i2.7604.
Y. Afrianto Singgalen, “Topic modeling using LDA and performance evaluation of classification algorithm: k-NN, SVM, NBC, and DT,” vol. 16, no. 3, pp. 143–157, Jun. 2024.
Y. Kustiyaningsih and Y. Permana, “Penggunaan Latent Dirichlet Allocation (LDA) dan Support-Vector Machine (SVM) Untuk Menganalisis Sentimen Berdasarkan Aspek Dalam Ulasan Aplikasi EdLink,” Teknika, vol. 13, no. 1, pp. 127–136, Mar. 2024, doi: 10.34148/teknika.v13i1.746.
E. Sa’dul Asyhar, S. Hadi Wijoyo, and N. Y. Setiawan, “Analisis Sentimen dan Pemodelan Topik Terhadap Ulasan Aplikasi Jenius Menggunakan Metode Support Vector Machine dan Latent Dirichlet Allocation,” Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer, vol. 8, no. 9, Sep. 2024, [Online]. Available: http://j-
P. A. Prastyo, B. Berlilana, and I. Tahyudin, “Analisis Sentimen dan Pemodelan Topik pada Ulasan Pengguna Aplikasi myIM3 Menggunakan Support Vector Machine dan Latent Dirichlet Allocation,” Building of Informatics, Technology and Science (BITS), vol. 6, no. 3, pp. 1618–1626, Dec. 2024, doi: 10.47065/bits.v6i3.6268.
Z. Jiang, V. Liu, and M. Erne, “Examining the Usefulness of Customer Reviews for Mobile Applications: The Role of Developer Responsiveness,” Journal of Database Management, vol. 35, no. 1, pp. 1–23, 2024, doi: 10.4018/JDM.343543.
H. Hassani, C. Beneki, S. Unger, M. T. Mazinani, and M. R. Yeganegi, “Text mining in big data analytics,” Big Data and Cognitive Computing, vol. 4, no. 1, pp. 1–34, Mar. 2020, doi: 10.3390/bdcc4010001.
H. Yan, M. Ma, Y. Wu, H. Fan, and C. Dong, “Overview and analysis of the text mining applications in the construction industry,” Heliyon, vol. 8, no. 12, p. e12088, Dec. 2022, doi: 10.1016/J.HELIYON.2022.E12088.
A. Nurian and B. Nurina Sari, “Analisis Sentimen Ulasan Pengguna Aplikasi Google Play Menggunakan Naïve Bayes,” Jurnal Informatika dan Teknik Elektro Terapan, vol. 11, no. 3, pp. 2830–7062, Sep. 2023, doi: 10.23960/jitet.v11i3%20s1.3348.
F. Noor Hasan and M. Dwijayanti, “Analisis Sentimen Pada Ulasan Pelanggan Menggunakan Metode Naïve Bayes Classifier (Studi Kasus: Grab Indonesia),” Jurnal Linguistik Komputasional, vol. 4, no. 2, pp. 93–99, Sep. 2021, doi: 10.22236/teknoka.v6i1.441.
P. Cichosz, “BAG OF WORDS AND EMBEDDING TEXT REPRESENTATION METHODS FOR MEDICAL ARTICLE CLASSIFICATION,” International Journal of Applied Mathematics and Computer Science, vol. 33, no. 4, pp. 603–621, Dec. 2023, doi: 10.34768/amcs-2023-0043.
M. Das, S. Kamalanathan, and P. Alphonse, “A Comparative Study on TF-IDF feature Weighting Method and its Analysis using Unstructured Dataset,” arXiv preprint arXiv:2308.04037, 2020.
L. T. Nguyen et al., “Evaluating the Performance of Topic Modeling Techniques for Bibliometric Analysis Research: An LDA-based Approach,” HighTech and Innovation Journal, vol. 5, no. 2, pp. 312–330, Jun. 2024, doi: 10.28991/HIJ-2024-05-02-07.
R. Guido, S. Ferrisi, D. Lofaro, and D. Conforti, “An Overview on the Advancements of Support Vector Machine Models in Healthcare Applications: A Review,” Information (Switzerland), vol. 15, no. 4, Apr. 2024, doi: 10.3390/info15040235.
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
