PENERAPAN DEEP LEARNING CONVOLUTIONAL NEURAL NETWORK DENGAN PHYTON UNTUK ANALISIS SENTIMEN PRODUK SKINCARE
DOI:
https://doi.org/10.31849/9x0h2n16Keywords:
Convolutional Neural Network, Klasifikasi Teks, Review Produk, Skincare, Deep LearningAbstract
Perkembangan industri skincare di Indonesia mengalami peningkatan yang cukup pesat seiring meningkatnya kesadaran masyarakat terhadap perawatan kulit. Banyaknya ulasan konsumen pada platform e-commerce dapat dimanfaatkan untuk mengetahui kecenderungan opini pengguna terhadap suatu produk. Namun, jumlah ulasan yang sangat besar membuat proses analisis secara manual menjadi kurang efektif. Oleh karena itu, penelitian ini bertujuan untuk menerapkan algoritma Convolutional Neural Network (CNN) dalam melakukan klasifikasi sentimen ulasan produk skincare secara otomatis. Dataset yang digunakan diperoleh dari Kaggle dengan jumlah 8.629 data ulasan produk skincare. Tahapan penelitian meliputi labeling data, preprocessing teks berupa cleansing, lowercasing, tokenizing, stopword removal, sequences, dan padding, kemudian dilanjutkan dengan proses pelatihan model CNN menggunakan Python dengan pustaka TensorFlow dan Keras. Untuk mengatasi ketidakseimbangan data antara kelas positif dan negatif, penelitian ini menerapkan parameter class weight pada proses pelatihan model. Hasil penelitian menunjukkan bahwa model CNN mampu menghasilkan akurasi sebesar 76% dengan nilai macro average F1-score sebesar 0,73. Model lebih baik dalam mendeteksi sentimen positif dibandingkan sentimen negatif karena distribusi data yang tidak seimbang. Meskipun demikian, CNN dinilai cukup efektif untuk diterapkan dalam analisis sentimen ulasan skincare berbahasa Indonesia dan dapat digunakan sebagai sistem pendukung keputusan awal bagi konsumen maupun pelaku bisnis e-commerce.
References
[1] R. H. Nadia Dwi Oktaviani1, “Pengaruh Kualitas Produk Dan Ewom Terhadap Keputusan Pembelian Skincare Pada E-Commerce Shopee,” Digit. Bus. Entrep. J. Vol., vol. 3, no. 1, pp. 36–46, 2025.
[2] Y. Lecun et al., “Gradient-based learning applied to document recognition To cite this version : HAL Id : hal-03926082 Gradient-Based Learning Applied to Document Recognition,” vol. 86, no. 11, pp. 2278–2324, 2023.
[3] H. Murfi, S. Theresia Gowandi, G. Ardaneswari, and S. Nurrohmah, “BERT-based combination of convolutional and recurrent neural network for indonesian sentiment analysis,” Appl. Soft Comput., vol. 151, pp. 1–15, 2024, doi: 10.1016/j.asoc.2023.111112.
[4] R. Johnson and T. Zhang, “Effective use of word order for text categorization with convolutional neural networks,” NAACL HLT 2015 - 2015 Conf. North Am. Chapter Assoc. Comput. Linguist. Hum. Lang. Technol. Proc. Conf., no. 2011, pp. 103–112, 2015, doi: 10.3115/v1/n15-1011.
[5] M. M. Cnn and R. N. N. Svm, “Analisis Sentimen Terhadap Produk Skincare,” vol. 5, no. 2, pp. 125–135, 2025.
[6] W. F. Setiawan, A. Amirullah, I. P. Ariatama, R. Nur, and E. Anggraini, “ES,” vol. 20, no. 1, pp. 77–91, 2026.
[7] S. H. Badjrie, O. N. Pratiwi, and H. D. Anggana, “Analisis Sentimen Review Customer Terhadap Produk Indihome dan First Media Menggunakan Algoritma Convolutional Neural Network Review Analysis Sentiment Customer Product Indihome and First Media Using Convolutional Neural Network,” eProceedings …, vol. 8, no. 5, pp. 9049–9061, 2021.
[8] G. Y. Sitio, A. Rumapea, and D. P. Lumbanraja, “Analisis Sentimen Pemindahan Ibu Kota Negara Di Media Sosial Twitter Menggunakan metode Convolutional Neural Network (CNN),” Methotika J. Ilm. Tek. Inform., vol. 3, no. 2, pp. 97–104, 2023.
[9] E. Lathifah, A. Dwi, P. Wicaksono, and A. R. Wijaya, “Penerapan Algoritma Convolutional Neural Network dalam Analisis Sentimen Pengaruh Brand Image dan Albel Harga (Studi Kasus: Produk Skincare Skintific),” Positif J. Sist. dan Teknol. Inf. , vol. Volume 10, no. 2, 2024.
[10] S. Informatika, U. Udayana, J. Raya, K. Udayana, B. Jimbaran, and K. Selatan, “Aspect Based Sentiment Analysis Terhadap Ulasan Produk Skincare di E-Commerce Menggunakan CNN-LSTM,” vol. 3, pp. 261–270, 2025.
[11] T. Astuti and R. Toyib, “Sentiment Analysis Sudut Pandang Generasi Z Terhadap Keterwakilan Kepemimpinan Muda Pilpres Di Twitter Mengunakan Id Convulation Neural Network,” Djtechno J. Teknol. Inf., vol. 5, no. 2, pp. 275–288, 2024, doi: 10.46576/djtechno.v5i2.4653.
[12] J. Camacho-Collados and M. T. Pilehvar, “On the Role of Text Preprocessing in Neural Network Architectures: An Evaluation Study on Text Categorization and Sentiment Analysis,” EMNLP 2018 - 2018 EMNLP Work. BlackboxNLP Anal. Interpret. Neural Networks NLP, Proc. 1st Work., pp. 40–46, 2018, doi: 10.18653/v1/w18-5406.
[13] A. N. Azhar, “Fine-tuning Pretrained Multilingual BERT Model for Indonesian Aspect-based Sentiment Analysis,” 2020.
[14] A. Pambudi and S. Suprapto, “Effect of Sentence Length in Sentiment Analysis Using Support Vector Machine and Convolutional Neural Network Method,” IJCCS (Indonesian J. Comput. Cybern. Syst., vol. 15, no. 1, p. 21, 2021, doi: 10.22146/ijccs.61627.
Downloads
Published
Issue
Section
License
Copyright (c) 2026 ZONAsi: Jurnal Sistem Informasi
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
CC BY-SA 4.0
Attribution-ShareAlike 4.0
You are free to:
- Share — copy and redistribute the material in any medium or format for any purpose, even commercially.
- Adapt — remix, transform, and build upon the material for any purpose, even commercially.
- The licensor cannot revoke these freedoms as long as you follow the license terms.
Under the following terms:
- Attribution — You must give appropriate credit , provide a link to the license, and indicate if changes were made . You may do so in any reasonable manner, but not in any way that suggests the licensor endorses you or your use.
- ShareAlike — If you remix, transform, or build upon the material, you must distribute your contributions under the same license as the original.
- No additional restrictions — You may not apply legal terms or technological measures that legally restrict others from doing anything the license permits.
Notices:
You do not have to comply with the license for elements of the material in the public domain or where your use is permitted by an applicable exception or limitation .
No warranties are given. The license may not give you all of the permissions necessary for your intended use. For example, other rights such as publicity, privacy, or moral rights may limit how you use the material.
