Chrome Extension Deteksi Spam Judi Online Pada Platform YouTube Menggunakan Ekstraksi Fitur dan Machine Learning
DOI:
https://doi.org/10.30865/jurikom.v15i5.9944Keywords:
Judi Online, Live Chat Youtube, Klasifikasi Teks, Count Vectorizer, TF-IDFAbstract
Penelitian mengklasifikasikan chat judi online pada fitur live chat YouTube menggunakan machine learning, karena pesan spam promosi judi sulit dimoderasi secara manual akibat volumenya yang tinggi dan bersifat real-time. Model klasifikasi teks dibangun dan dibandingkan menggunakan ekstraksi fitur Count Vectorizer dan TF-IDF yang dikombinasikan dengan Support Vector Machine (SVM) dan Random Forest pada data live chat YouTube berlabel biner “JUDOL” dan “NORMAL”. Evaluasi menggunakan accuracy, precision, recall, F1-score, confusion matrix, dan Stratified K-Fold Cross Validation. Kata seperti “slot”, “gacor”, “freebet”, dan “wisdomtoto” menjadi indikator penting pesan judi online. Seluruh kombinasi menghasilkan akurasi di atas 99,8% pada Stratified 10-Fold Cross Validation dengan perbedaan antar-metode dalam kisaran simpangan baku. Count Vectorizer dengan SVM memperoleh rata-rata F1-score CV tertinggi (0,9990 ± 0,0010) serta akurasi dan F1-score 99,92% pada data uji independen. Model terbaik dideploy pada Chrome Extension yang terhubung dengan REST API lokal, dengan latensi inferensi rata-rata 0,46 ms per pesan, throughput 2.164 pesan per detik, dan latensi end-to-end 3,19 ms pada lingkungan 1 vCPU. Sistem tetap stabil hingga 200 pesan per detik sehingga mendukung penyaringan spam pada siaran langsung bervolume tinggi. Namun, repetisi template spam pada dataset dapat memengaruhi tingginya performa, sehingga generalisasi terhadap pola spam baru perlu diuji lebih lanjut.
References
[1] M. N. Sari and J. Veri, “PERAN MEDIA SOSIAL DALAM KOMUNIKASI PUBLIK DI ERA DIGITAL: KAJIAN LITERATUR SISTEMATIS BERBASIS PRISMA,” Jurnal Daya Saing, vol. 11, no. 3, pp. 669–677, Oct. 2025.
[2] H. Lin, “`Let’s purchase coloured live chat messages’: the impact of user engagement with Super Chat on YouTube,” Inf. Commun. Soc., vol. 28, no. 9, pp. 1608–1626, Jul. 2025.
[3] A. Fahrudin et al., “Online gambling addiction: Problems and solutions for policymakers and stakeholders in Indonesia,” J. Infrastruct. Pol. Dev., vol. 8, no. 11, p. 9077, Oct. 2024.
[4] P. A. N. Martha, “Legal review of online gambling crimes in Indonesia and its impact on the younger generation,” Journal of Social Research, vol. 4, no. 8, pp. 2213–2218, Aug. 2025.
[5] E. Yang, D. D. Lewis, and O. Frieder, “TAR on social media: A framework for online content moderation,” Aug. 2021.
[6] J. S. Andersen, O. Zukunft, and W. Maalej, “REM: Efficient semi-automated real-time moderation of online forums,” in Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing: System Demonstrations, Stroudsburg, PA, USA: Association for Computational Linguistics, 2021.
[7] A. C. Zahro et al., “Fairer Public Complaint Classification on LaporGub: Integrating XLM-RoBERTa with Focal Loss for Imbalance Data,” sinkron, vol. 9, no. 4, pp. 1850–1862, Oct. 2025, doi: 10.33395/sinkron.v9i4.15260.
[8] K. Szabó Nagy, J. Kapusta, and M. Munk, “Feature extraction from unstructured texts as a combination of the morphological and the syntactic analysis and its usage in fake news classification tasks,” Neural Comput. Appl., Sep. 2023.
[9] K. Dumbre, B. Shiragapur, Y. More, and V. Kale, “Enhanced frequency-based word embedding approach for text analysis: Comparative study with existing method,” in 2023 7th International Conference on Computer Applications in Electrical Engineering-Recent Advances (CERA), IEEE, Oct. 2023.
[10] S. Senbel, “Fast and memory-efficient TFIDF calculation for text analysis of large datasets,” in Advances and Trends in Artificial Intelligence. Artificial Intelligence Practices, in Lecture Notes in Computer Science. , Cham: Springer International Publishing, 2021, pp. 557–563.
[11] D. Kaibassova, B. Mukhametzhanova, D. Tokseit, A. Kubegenova, and M. Kozhanov, “Document analysis via combined vectorization and machine learning approaches,” ijirss, vol. 8, no. 4, pp. 2195–2204, Jul. 2025.
[12] Z. Labd, S. Bahassine, K. Housni, F. Z. A. Hamou Aadi, and K. Benabbes, “Text classification supervised algorithms with term frequency inverse document frequency and global vectors for word representation: a comparative study,” Int. J. Electr. Comput. Eng. (IJECE), vol. 14, no. 1, p. 589, Feb. 2024.
[13] S. Bose and S. Bose, “Random Forests: The wisdom of crowds in action,” Journal of Emerging Trends in Computer Science and Applications, vol. 1, no. 1, pp. 67–91, Nov. 2025.
[14] M. Maindola et al., “Utilizing random forests for high-accuracy classification in medical diagnostics,” in 2024 7th International Conference on Contemporary Computing and Informatics (IC3I), IEEE, Sep. 2024, pp. 1679–1685.
[15] Yaemico, “Dataset Judol Youtube Live Chat Ultah Jogja Ke-268,” Kaggle. Accessed: Jun. 01, 2026. [Online]. Available: https://www.kaggle.com/datasets/yaemico/deteksi-judi-online?select=youtube_chat_jogja_clean.csv
[16] M. Ariyanto, F. Alzami, R. Rakhmat Sani, I. Gamayanto, M. Naufal, and S. Winarno, “Addressing Extreme Class Imbalance in Multilingual Complaint Classification Using XLM-RoBERTa,” 2026. [Online]. Available: http://jurnal.polibatam.ac.id/index.php/JAIC
[17] P. Cichosz, “Bag of words and embedding text representation methods for medical article classification,” Int. J. Appl. Math. Comput. Sci., vol. 33, no. 4, 2023.
[18] H. S. Lubis, M. K. M. Nasution, and A. Amalia, “Performance of term frequency - inverse document frequency and K-means in government service identification,” in 2024 4th International Conference of Science and Information Technology in Smart Administration (ICSINTESA), IEEE, Jul. 2024, pp. 772–777.
[19] H. Bichri, A. Chergui, and M. Hain, “Investigating the impact of train / test split ratio on the performance of pre-trained models with custom datasets,” Int. J. Adv. Comput. Sci. Appl., vol. 15, no. 2, 2024.
[20] I. K. Nti, Department of Computer Science, U. of E. Informatics, G. Natural Resources Sunyani, O. Nyarko-Boateng, and J. Aning, “Performance of machine learning algorithms with different K values in K-fold CrossValidation,” Int. J. Inf. Technol. Comput. Sci., vol. 13, no. 6, pp. 61–71, Dec. 2021.
[21] R. Vinston Raja, J. Jayashankari, S. Sheela, S. Jancy Sickory Daisy, G. G. Gokilam, and M. Robinson Joel, “Metrics and techniques for evaluating machine learning models and optimization algorithms,” in Advances in Computational Intelligence and Robotics, IGI Global Scientific Publishing, 2025, pp. 193–222.
[22] Rafi Jonathan Siger, Muhammad Naufal, and Farrikh Alzami, “Analisis Performa Class Weight Dan Focal Loss Pada Model Indobert Untuk Klasifikasi Teks Depresi Berbahasa Indonesia,” JURIKOM (Jurnal Riset Komputer), vol. 13, no. 2, pp. 558–568, Apr. 2026, doi: 10.30865/jurikom.v13i2.9620.
