Klasifikasi Kinerja Konten YouTube Mobile Legends Menggunakan LightGBM dengan Pelabelan Berbasis K-Means dan Interpretasi SHAP
-
Wayan Praka
*
Universitas Teknologi Yogyakarta,
Indonesia
- Ella Kristiantini Susan Universitas Teknologi Yogyakarta, Indonesia
- Lidya Nurmala Eva Universitas Teknologi Yogyakarta, Indonesia
Abstract
YouTube is a video-sharing platform widely used by content creators, including those in the gaming category such as Mobile Legends. The intense competition among Mobile Legends content creators has made content performance analysis essential for developing data-driven content strategies. However, most previous studies have relied on manual data labeling, which is prone to subjectivity and lacks efficiency. Furthermore, high-accuracy classification models are often treated as black-box models, making it difficult to explain the factors influencing prediction outcomes. This study aims to develop a YouTube Mobile Legends content performance classification model by integrating K-Means, LightGBM, and Shapley Additive exPlanations (SHAP). The dataset consists of 3,052 videos collected using the YouTube Data API v3. The K-Means algorithm was employed to generate automatic labels, while LightGBM was used as the classification model and SHAP was applied to interpret the model's predictions. The results indicate that the optimal number of clusters was K=2, producing two performance classes: High Performance (72.44%) and Low Performance (27.56%). The dataset was subsequently divided into 80% for training and 20% for testing. On the testing dataset, the LightGBM model achieved an accuracy of 93.78%, precision of 93.87%, recall of 93.78%, and an F1-score of 93.81%. Furthermore, 10-fold cross-validation yielded a mean accuracy of 92.75% with a standard deviation of 0.0148, demonstrating the model's robustness and stability. SHAP analysis revealed that Subscriber Count was the most influential feature, followed by Duration, Video Age, and Title Length. These findings demonstrate that the integration of K-Means, LightGBM, and SHAP provides an effective approach for objectively, accurately, and transparently classifying the performance of Mobile Legends content on YouTube, while offering valuable insights to support content creators in developing data-driven content strategies.
References
A. Efstratiou, “On YouTube Search API Use in Research,” Association for Computing Machinery (ACM), pp. 919–927, Oct. 2025, doi: 10.1145/3730567.3764492.
S. Yang, D. Brossard, D. A. Scheufele, and M. A. Xenos, “The science of YouTube: What factors influence user engagement with online science videos?,” Journal PLoS ONE, vol. 17, no. 5, pp. 1–19, May 2022, doi: 10.1371/journal.pone.0267697.
C. Violot, T. Elmas, I. Bilogrevic, and M. Humbert, “Shorts vs. Regular Videos on YouTube: A Comparative Analysis of User Engagement and Content Creation Trends,” WEBSCI 24: Proceedings of the 16th ACM Web Science Conference, no. 1, pp. 213–223, May 2024, doi: 10.1145/3614419.3644023.
N. Charolin and A. Wedhasmara, “Evaluasi Keterlibatan Masyarakat di YouTube Pemerintah: Durasi, Judul, Dialog, Konten, Emosi,” Journal of Business and Information System, vol. 6, no. 1, pp. 131–144, Jun. 2024, doi: 10.36067/jbis.v6i1.234.
S. W. Tampubolon and P. Dirgantara, “Pengaruh Konten Youtube Oura Gaming Terhadap Pemenuhan Kebutuhan Informasi Mobile Legends,” Jurnal Ilmu Komunikasi UHO : Jurnal Penelitian Kajian Ilmu Sosial dan Informasi, vol. 8, no. 4, pp. 684–694, Oct. 2023, doi: 10.52423/jikuho.v8i4.142.
C. O. G. A. D. H. Uray, Vika, and C. Cahyaningtias, “Menelaah Kesuksesan Konten YouTube yang Trending Analisis Data Video Trending di YouTube,” Informatik: Jurnal Ilmu Komputer, vol. 20, no. 2, pp. 84–92, Aug. 2024, doi: 10.52958/iftk.v20i2.7517.
M. F. A. Mufid, E. Daniati, and A. Nugroho, “Analisis Sentimen Ulasan Aplikasi Mobile Legends Berbasis Pelabelan IndoBERT dan SMOTE dengan Komparasi Algoritma Klasifikasi Naive Bayes dan SVM,” Management of Information System Journal, vol. 4, no. 3, pp. 151–159, Jul. 2026, doi: 10.47065/mis.v2i3.2783.
M. Alfudola, N. Suarna, and I. Ali, “Klasifikasi Pemilihan Tipe Hero Mobile Legends Terhadap Minat Pemain Menggunakan Algorima Naive Bayes Studi Kasus: Komunitas Game Mobile Legends Kota Cirebon,” JATI: Jurnal Mahasiswa Teknik Informatika, vol. 7, no. 2, pp. 1269–1273, Apr. 2023, doi: 10.36040/jati.v7i2.6541.
M. Qi, J. Q. Zhao, and Y. Feng, “An optimized public opinion communication system in social media networks based on K-means cluster analysis,” Heliyon, vol. 10, no. 24, pp. 1–12, Nov. 2024, doi: 10.1016/j.heliyon.2024.e40033.
M. N. Afrilia, N. Rahaningsih, R. D. Dana, and N. D. Nuris, “Optimasi Analisis Clustering Untuk Aktivitas Dan Respon Pengguna Media Sosial Dengan K-Means,” JATI: Jurnal Mahasiswa Teknik Informatika, vol. 8, no. 1, pp. 148–155, Feb. 2024, doi: 10.36040/jati.v8i1.8334.
R. Y. Simanullang and M. Iqbal, “Pengelompokan Pola Interaksi Pengguna Media Sosial Menggunakan Algoritma K-Means untuk Pemetaan Aktivitas Online,” Journal of Informatics Management and Information Technology, vol. 6, no. 1, pp. 37–43, Jan. 2026, doi: 10.47065/jimat.v6i1.954.
A. R. Lahitani, A. N. Zhafarina, N. S. W. Oktavia, and N. Jariyah, “Pemetaan Topik Pembicaraan Pada Komentar Live Youtube Menggunakan K-Means Clustering sebagai Identifikasi awal Kejahatan Verbal Cyberbullying,” JTE UNIBA: Jurnal Teknik Elektro Uniba, vol. 8, no. 2, pp. 399–403, Apr. 2024, doi: 10.36277/jteuniba.v8i2.253.
Fathoni, N. A. Basulina, S. Gustiani, S. Amalia, A. Sabila, and A. Ibrahim, “Identifikasi Waktu Optimal Posting Terhadap Pola Engagement Sosial Media Menggunakan Metode K-Means Clustering,” JATI: Jurnal Mahasiswa Teknik Informatika, vol. 9, no. 4, pp. 6237–6244, Aug. 2025, doi: 10.36040/jati.v9i4.14027.
S. K. Sitanggang, F. R. Umbara, and H. Ashaury, “Klasifikasi Video Pada Media Sosial Youtube Dengan Menggunakan Metode K-Means Dan Support Vector Machine,” Jurnal Locus Penelitian dan Pengabdian, vol. 2, no. 10, pp. 1027–1032, Oct. 2023, doi: 10.58344/locus.v2i10.1732.
W. A. Aristawidya and M. Rahardi, “A Hybrid Approach to Music Recommendations Based on Audio Similarity Using Autoencoder and LightGBM,” Journal of Applied Informatics and Computing (JAIC), vol. 9, no. 6, pp. 3191–3197, Dec. 2025, doi: 10.30871/jaic.v9i6.10516.
R. Jannah and R. Prathivi, “Analisa Performa Metode Lightgbm Untuk Prediksi Kecanduan Media Sosial,” Jurnal Transformatika, vol. 23, no. 2, pp. 164–173, Jan. 2026, doi: 10.26623/transformatika.v23i2.13165.
A. N. Royana, Y. V. Via, and C. A. Putra, “Evaluasi Kinerja Lightgbm Dan Catboost Untuk Prediksi Churn Berdasarkan Dataset Pelanggan Layanan Streaming Musik,” JATI: Jurnal Mahasiswa Teknik Informatika, vol. 9, no. 4, pp. 6977–6982, Aug. 2025, doi: 10.36040/jati.v9i4.14358.
Moch. A. Aprihartha and I. Idham, “Optimization of Classification Algorithms Performance with k-Fold Cross Validation,” Eigen Mathematics Journal, vol. 7, no. 2, pp. 61–66, Dec. 2024, doi: 10.29303/emj.v7i2.212.
A. M. Salih et al., “A Perspective on Explainable Artificial Intelligence Methods: SHAP and LIME,” Advanced Intelligent Systems, vol. 7, no. 1, pp. 1–8, Jan. 2025, doi: 10.1002/aisy.202400304.
Y. F. Saputra et al., “Ensemble Learning untuk Model Prediksi Risiko Preeklamsia dan Explainable Ai Berbasis SHAP,” Metik Jurnal, vol. 10, no. 1, p. 2026, Jun. 2026, doi: 10.47002/kp377403.
Copyright (c) 2026 Wayan Praka, Ella Kristiantini Susan, Lidya Nurmala Eva
This work is licensed under a Creative Commons Attribution 4.0 International License.
Authors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under Creative Commons Attribution 4.0 International License that allows others to share the work with an acknowledgment of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgment of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (Refer to The Effect of Open Access).
.png)
.png)
