Analisis Faktor Kepuasan Pelanggan Produk Skincare di Tiktok Shop Menggunakan Machine Learning dan Shap
DOI:
https://doi.org/10.55123/insologi.v5i4.9057Keywords:
Customer Satisfaction, Sentiment Analysis, Random Forest, SHAP, Tiktok ShopAbstract
Customer reviews of skincare products sold through TikTok Shop provide valuable information for evaluating customer satisfaction and understanding consumer preferences. As the volume of reviews continues to grow, manual analysis becomes increasingly inefficient, making machine learning-based sentiment analysis a more effective approach. This study applies the Random Forest algorithm to classify customer sentiment and employs Shapley Additive Explanations (SHAP) to interpret the factors influencing the model's predictions. The study utilized a dataset of 663 customer reviews collected from TikTok Shop. The analysis process consisted of text preprocessing, TF-IDF feature extraction, sentiment labeling, Random Forest model development, performance evaluation, and model interpretation using SHAP. The experimental results showed that the proposed model achieved an accuracy of 68.42%, a precision of 67.79%, a recall of 68.42%, and an F1-score of 67.29%. Of the total reviews analyzed, 341 reviews (51.43%) were classified as positive, 208 reviews (31.37%) as negative, and 114 reviews (17.19%) as neutral. SHAP analysis revealed that the terms "banget," "bagus," "bikin," "Skintific," and "kulit" were the most influential features affecting the model's predictions of customer satisfaction. These findings provide useful insights for businesses to better understand customer perceptions and support continuous improvements in product quality and service performance.
Downloads
References
Chandra, W. (2024). Kepuasan Pelanggan Di Tiktok Shop. Jurnal Manajerial dan Kewirausahaan 06(02), 552–558.
Cucun Very Angkoso, Mochamad Adrian Nuradha Thrisna, Budi Dwi Satoto, A. K. (2024). Optimasi Klasifikasi Sentimen Menggunakan. Jurnal Edukasi dan Penelitian Informatika, 10(3), 389–400.
Dewi, T., & Afrillia, Y. (2025). Sentiment Analysis of Customer Satisfaction Towards Shopee and Lazada E-commerce Platform Using the Random Forest Algorithm Classifier. International Journal of Engineering, Science and Information Technology, 5(1), 229–235. https://doi.org./10.52088/ijesty.v5i1.692
Fitria, N., Nurkasih, S. L., & Aulia, N. D. (2026). Pengaruh Kualitas Sistem TikTok Shop terhadap Kepuasan Pelanggan Dalam Pembelian Produk Fashion Online. 5(1), 45–51.
Harmandini, K. P., & L, K. M. (2024). Analysis of TF-IDF and TF-RF Feature Extraction on Product Review Sentiment. Sinkron: Jurnal dan Penelitian Teknologi Informatika, 8(2), 929–937.
Iffadah, A. S., & Prasetya, D. A. (2025). Shapley Additive Explanations Interpretation of the XGBoost Model in Predicting Air Quality in Jakarta. Jurnal Riset Informatika, 7(3). https://doi.org/10.34288/jri.v7i3.366
Komputer, F. I., & Pamulang, U. (2025). Penerapan Algoritma Random Forest Berbasis TF – IDF untuk Meningkatkan untuk Akurasi Deteksi Sentimen Ulasan Produk E- Commerce. Riau Jurnal Informatika, 4(3), 454–459.
Lestari, V. B., & Hutagalung, C. A. (n.d.). Evaluation of TF-IDF Extraction Techniques in Sentiment Analysis of Indonesian-Language Marketplaces Using SVM , Logistic Regression , and Naive Bayes. Journal of Computer Science and Applications, 021, 36–44. https://doi.org/10.21009/j-koma.v8i1.05
Nur, M. A., Umar, N., Feng, Z., & Gani, H. (2025). Evaluation Of Indobert And Roberta : Performance Of Indonesian Language Transformer Models In Sentiment. JIKO: Jurnal Informatika dan Komputer, 8(0173), 121–127. https://doi.org/10.33387/jiko.v8i2.9988
Puspanagara, A. L. (2025). Penerapan Explainable AI untuk Prediksi Performa Akademik Mahasiswa Menggunakan Random Forest dan SHAP. Infoman's: Jurnal Ilmu-ilmu Informatika dan Manajemen, 19(1), 1–7.
Saputra, F. (2025). Prediction Customer Loyalty Using Random Forest Algorithm on Shopee Reviews.
Junral Universitas Bina Sarana Informatika, 27(1), 11–20. https://doi.org/10.31294/p.v27i1.7940 Sari, P. W., Kadafi, A. R., Bina, U., & Informatika, S. (2025). Perbandingan Algoritma Random Forest
Dan Naïve Bayes Dalam Menganalisis Sentimen Ulasan Pada Produk Skincare Lokal Di Media. JITET (Jurnal Informatika dan Teknik Elektro Terapan) 13(3), 1946–1957. http://dx.doi.org/10.23960/jitet.v13i3S1.8150
Setiawan, Y., Purwandari, E. P., Wijanarko, A., Panca, Y. P., & Utama, F. P. (2025). Detection of Bahasa cyberbullying speech using large-scale N-gram machine learning models with increased document-terms probability. Bol. Soc. Paran. Mat., 43(4), 1–14. https://doi.org/10.5269/bspm.78695
Winanta, H. P., Hana, M. Y., & Hasan, F. N. (2026). Comparative Analysis of Explainable AI Methods LIME , SHAP , and ELI5 on Random Forest Based Indonesian E-Commerce Sentiment Classification. Jurnal Teknik Informatika (JUTIF), 7(2), 1778–1799. https://doi.org/10.52436/1.jutif.2026.7.2.5642
Wu, Q., Xia, C., & Tian, S. (n.d.). AI-Driven Sentiment Analytics : Unlocking Business Value in the E-Commerce Landscape.
Wulandary, E., Mas, M., & Ashoer, M. (2023). Pengaruh Kualitas Layanan Era Digitalisasi Media Pemasaran Online E-Commerce dengan Menggunakan E-Service Quality Untuk Mengetahui Kepuasan Pelanggan. Center of Economic Student Journal, 6(1), 44–59. https://doi.org/10.56750/csej.v6i1.568
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2026 Selma Mulkya Nisa, Yudi Setiawan, Endina Putri Purwandari
This work is licensed under a Creative Commons Attribution 4.0 International License.
Hak cipta pada setiap artikel adalah milik penulis.
Penulis mengakui bahwa INSOLOGI (Jurnal Sains dan Teknologi) sebagai publisher yang mempublikasikan pertama kali dengan lisensi Creative Commons Attribution 4.0 International License.
Penulis dapat memasukan tulisan secara terpisah, mengatur distribusi non-ekskulif dari naskah yang telah terbit di jurnal ini kedalam versi yang lain, seperti: dikirim ke respository institusi penulis, publikasi kedalam buku, dan lain-lain. Dengan mengakui bahwa naskah telah terbit pertama kali pada INSOLOGI (Jurnal Sains dan Teknologi).
