Kategorisasi Komentar Live Streaming TikTok Menggunakan Support Vector Machine

Meythia Maharani; Mochamad Chairul  Ihsan

doi:10.31004/riggs.v5i1.6636

Authors

Meythia Maharani Universitas Padjadjaran
Mochamad Chairul Ihsan Universitas Padjadjaran

DOI:

https://doi.org/10.31004/riggs.v5i1.6636

Keywords:

Live Streaming, TikTok, Kategorisasi Komentar, Support Vector Machine, Social Commerce

Abstract

Di era social commerce yang berkembang pesat, live streaming telah menjadi alat pemasaran yang krusial, khususnya dalam industri kecantikan. Penelitian ini bertujuan untuk menganalisis dan mengklasifikasikan karakteristik komentar audiens pada live streaming TikTok dari brand Make Over. Analisis difokuskan pada perbandingan dua konteks waktu yang berbeda, yaitu sesi Business as Usual (BAU) dan kampanye Payday, dengan menerapkan algoritma Support Vector Machine (SVM). Data penelitian dikumpulkan melalui teknik scraping untuk mendapatkan himpunan komentar dari kedua sesi live streaming tersebut. Tahapan metode penelitian diawali dengan prapemrosesan teks yang komprehensif untuk membersihkan noise pada data. Selanjutnya, proses pelabelan kategori komentar dilakukan secara otomatis memanfaatkan teknologi Large Language Model (LLM) GPT-4o mini untuk meningkatkan efisiensi. Fitur diekstraksi menggunakan metode pembobotan Term Frequency-Inverse Document Frequency (TF-IDF). Untuk mengatasi masalah ketidakseimbangan kelas pada dataset, penelitian ini mengimplementasikan teknik Synthetic Minority Over-sampling Technique (SMOTE) sebelum melatih model SVM. Hasil pengujian model menunjukkan adanya perbedaan karakteristik interaksi yang signifikan antara kedua sesi. Sesi Payday menghasilkan volume komentar yang jauh lebih tinggi dan didominasi oleh niat transaksional, seperti pertanyaan seputar diskon dan voucher, mencapai akurasi klasifikasi sebesar 92,62%. Sebaliknya, sesi BAU lebih didominasi oleh komentar bersifat konsultatif terkait kecocokan produk dengan akurasi model 84,54%. Meski demikian, kategori Information Seeking tetap menjadi yang paling dominan di kedua sesi. Temuan strategis ini memberikan implikasi manajerial bagi brand, menyarankan perlunya strategi pengelolaan live streaming yang lebih adaptif berdasarkan konteks waktu promosi serta perilaku spesifik audiens.

Downloads

Download data is not yet available.

References

ACerbi, A. (2016). A cultural evolution approach to digital media. Frontiers in Human Neuroscience, 10, 636. https://doi.org/10.3389/fnhum.2016.00636

Ali, M., Yasmine, F., Mushtaq, H., Sarwar, A., Idrees, A., Tabassum, S., Hayyat, B., & Ur Rehman, K. (2021). Customer opinion mining by comments classification using machine learning. International Journal of Advanced Computer Science and Applications, 12(5), 385–393.

Alomari, E. A. (2024). Unlocking the potential: A comprehensive systematic review of ChatGPT in natural language processing tasks. Computer Modeling in Engineering & Sciences, 141(1), 43–85.

https://doi.org/10.32604/cmes.2024.052256

Appel, G., Grewal, L., Hadi, R., & Stephen, A. T. (2020). The future of social media in marketing. Journal of the Academy of Marketing Science, 48(1), 79–95.

https://doi.org/10.1007/s11747-019-00695-1

Aprianto, W., Sari, D. P., & Wahdini. (2024). Examining influencers’ role in TikTok shop’s promotional strategies and their impact on consumer purchase intentions. Jurnal Informatika Ekonomi Bisnis, 6(2), 1–8.

https://doi.org/10.37034/infeb.v6i2.273

Bacay, J. L., Bacay, C. C., & Reynon, G. I. C. (2025). Scarcity marketing: The role of consumer behavior in the rise of the “Anik-Anik”. International Journal of Social Sciences and Humanities Invention, 12(1), 8415–8422.

https://doi.org/10.18535/ijsshi/v12i01.01

Bhardwaj, R., Singh, R. S., Singh, J., Singh, S. P., Singh, A., & Kumar, V. (2024). Sentiment analysis of live stream comments using machine learning algorithms. In Proceedings of the 4th International Conference on Innovative Practices in Technology and Management (ICIPTM).

https://doi.org/10.1109/ICIPTM59628.2024.10563700

Brodie, R. J., Hollebeek, L. D., Jurić, B., & Ilić, A. (2011). Customer engagement: Conceptual domain, fundamental propositions, and implications for research. Journal of Service Research, 14(3), 252–271.

https://doi.org/10.1177/1094670511411703

Datareportal. (2025). Digital 2025: Indonesia.

https://datareportal.com/reports/digital-2025-indonesia

Dwivedi, Y. K., Ismagilova, E., Hughes, D. L., Carlson, J., Filieri, R., Jacobson, J., Jain, V., Karjaluoto, H., Kefi, H., Krishen, A. S., Kumar, V., Rahman, M. M., Raman, R., Rauschnabel, P. A., Rowley, J., Salo, J., Tran, G. A., & Wang, Y. (2021). Setting the future of digital and social media marketing research. International Journal of Information Management, 59, 102168. https://doi.org/10.1016/j.ijinfomgt.2020.102168

Fide, S., Suparti, S., & Sudarno, S. (2021). Analisis sentimen ulasan aplikasi TikTok di Google Play menggunakan metode Support Vector Machine (SVM). Jurnal Gaussian, 10(3), 346–358.

Hajli, M. N. (2024). A study of the impact of social media on consumers. International Journal of Market Research, 56(3), 387–404. https://doi.org/10.2501/IJMR-2014-025

Kaplan, A. M., & Haenlein, M. (2010). Users of the world, unite! The challenges and opportunities of social media. Business Horizons, 53(1), 59–68.

https://doi.org/10.1016/j.bushor.2009.09.003

Kufel, J., Bargieł-Łączek, K., Kocot, S., Koźlik, M., Bartnikowska, W., Janik, M., Czogalik, Ł., Dudek, P., Magiera, M., Lis, A., Paszkiewicz, I., Nawrat, Z., Cebula, M., & Gruszczyńska, K. (2023). What is machine learning, artificial neural networks and deep learning? Diagnostics, 13(15), 2582.

https://doi.org/10.3390/diagnostics13152582

Liang, T.-P., & Turban, E. (2011). Introduction to the special issue social commerce. International Journal of Electronic Commerce, 16(2), 5–14. https://doi.org/10.2753/JEC1086-4415160201

Liao, J., Chen, K., Qi, J., Li, J., & Yu, I. Y. (2023). Creating immersive and parasocial live shopping experience for viewers. Journal of Research in Interactive Marketing, 17(1), 140–155.

https://doi.org/10.1108/JRIM-04-2021-0114

Miao, H., Yin, Y., Zhao, Y., & Gao, Q. (2025). Key elements and theoretical logic of live streaming e-commerce marketing discourse. PLOS ONE, 20(5), e0322495.

https://doi.org/10.1371/journal.pone.0322495

Medina Serrano, J. C., Papakyriakopoulos, O., & Hegelich, S. (2020). Dancing to the partisan beat: A first analysis of political communication on TikTok. In Proceedings of the 12th ACM Conference on Web Science, 257–266. https://doi.org/10.1145/3394231.3397916

Pakpahan, D., Siallagan, V., & Siregar, S. D. (2023). Classification of e-commerce product descriptions with TF-IDF and SVM methods. Sinkron: Jurnal dan Penelitian Teknik Informatika, 7(4), 2130–2137.

https://doi.org/10.33395/sinkron.v8i4.12779

Park, H. J., & Lin, L.-M. (2020). The effects of match-ups on the consumer attitudes toward internet celebrities and their live streaming content. Journal of Retailing and Consumer Services, 52, 101934.

https://doi.org/10.1016/j.jretconser.2019.101934

Rahmah, N., Hidayat, N., & Az-Zahra, H. M. (2023). Analisis kinerja Support Vector Machine dalam mengidentifikasi ujaran kebencian pada media sosial Twitter. Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer, 7(7), 3568–3575.

Rahmawati, W., Fuadi, W., & Afrillia, Y. (2024). Cosmetic shop sentiment analysis on TikTok Shop using the support vector machine method. International Journal of Engineering, Science & Information Technology, 4(2), 31–37.

https://doi.org/10.52088/ijesty.v4i1.498

Rizki, A. M., Bustami, & Anshari, S. F. (2025). Comparison of Support Vector Machine and Naïve Bayes algorithms in sentiment analysis of TikTok Shop application user reviews. Journal of Renewable Energy, Electrical, and Computer Engineering, 5(1), 18–29. https://doi.org/10.29103/jreece.v5i1.21342

Sarker, I. H. (2021). Machine learning: Algorithms, real-world applications and research directions. SN Computer Science, 2(3), 160. https://doi.org/10.1007/s42979-021-00592-x

Suvarna, S. V., & Malagi, A. K. (2023). Impact of time limited promotions on online consumer behaviour. International Journal of Advanced Research, 11(6), 991–996.

https://doi.org/10.21474/IJAR01/17157

The Straits Times. (2023, September 25). Indonesia entrepreneurs cash in on TikTok live-selling spree. https://www.straitstimes.com/asia/se-asia/indonesia-entrepreneurs-cash-in-tiktok-live-selling-spree

Wongkitrungrueng, A., & Assarut, N. (2020). The role of live streaming in building consumer trust and engagement with social commerce sellers. Journal of Business Research, 117, 543–556.

https://doi.org/10.1016/j.jbusres.2018.08.032

Zerodytrash. (2024). TikTok-Live-Connector. GitHub repository.

https://github.com/zerodytrash/TikTok-Live-Connector

Zhang, M., & Zhang, J. (2025). Socializing or information seeking: Which should be prioritized for response in live streaming messages? Journal of Systems Science and Systems Engineering, 34(3), 306–333.

https://doi.org/10.1007/s11518-025-5645-0

Zhao, W. (2020). Classification of customer reviews on e-commerce platforms based on Naïve Bayesian algorithm and support vector machine. Journal of Physics: Conference Series, 1678, 012081.

https://doi.org/10.1088/1742-6596/1678/1/012081