Customer Comment Clustering for Kahf Face Wash at Kahf Official Shop Using K-Means Method
DOI:
https://doi.org/10.64878/jistics.v1i3.23Keywords:
Clustering, K-means, Comments, Consumers, TF-IDF, Kahf, ShopeeAbstract
The advancement of information technology has encouraged people to shop more confidently, including for men's skincare products. Although data indicate that men's interest in skincare remains relatively low, sales of Kahf Face Wash show high figures. In this context, consumer reviews on e-commerce platforms serve as a valuable source of information for understanding customer satisfaction and experience. This study aims to group consumer comments on Kahf Face Wash products from the Kahf Official Shop using the K-Means clustering method. A total of 4,966 consumer comments were collected automatically through web crawling techniques. These comments then underwent several text processing stages, including case folding, cleaning, tokenization, normalization, removal of stop words, and stemming. After the cleaning process, 2,431 comments remained for analysis. The textual data was transformed into numerical representations using the TF-IDF method, and the optimal number of clusters was determined using the Elbow method, which indicated the optimal value at k = 3. The clustering results categorized the comments into three groups: purchase experience (1,506 comments), product effectiveness (474 comments), and delivery and service (451 comments). Visualization was conducted using PCA and bar charts to better illustrate the distribution and proportion of comments in each cluster. Evaluation of the clustering results using inertia and the Davies–Bouldin Index revealed that the model effectively grouped the comments with a reasonably high quality. This study makes a significant contribution by helping companies analyze customer behavior through an unsupervised learning approach. This method enables companies to efficiently extract structured insights from unstructured reviews, which can be utilized to enhance service quality, marketing strategies, and future product development.
Downloads
References
P. Ani, “Number of internet and social media users worldwide as of February 2025,” Worldwide: Ani Petrosyan, 2025, p. 1.
Y. W. Syaifudin and R. A. Irawan, “Implementasi Analisis Clustering Dan Sentimen Data Twitter Pada Opini Wisata Pantai Menggunakan Metode K-Means,” J. Inform. Polinema, vol. 4, no. 3, pp. 189–194, 2018, doi: 10.33795/jip.v4i3.205. DOI: https://doi.org/10.33795/jip.v4i3.205
Santos, “Online Shopping Demographics,” Steven, Ed., Indonesia: santos, 2025.
Septianda Reza Maulana, Luqman Affandi, and Mamluatul Haniah, “Sistem Pakar Diagnosa Penyakit Paru-Paru Menggunakan Metode Case Based Reasoning,” J. Inform. Polinema, vol. 9, no. 2, pp. 193–200, 2023, doi: 10.33795/jip.v9i2.1225. DOI: https://doi.org/10.33795/jip.v9i2.1225
R. Firmansyah, “Inilah Data Penjualan Produk Kahf Facial Wash pada Tahun 2020-2022,” p. 1, 2024.
M. R. B. Kencana, “Kemendag Terima 1.568 Pengaduan Konsumen di Kuartal I 2025, Belanja Online Paling Banyak,” Jakarta, 2025, p. 1.
F. Indriyani and E. Irfiani, “Clustering Data Penjualan pada Toko Perlengkapan Outdoor Menggunakan Metode K-Means,” JUITA J. Inform., vol. 7, no. 2, p. 109, 2019, doi: 10.30595/juita.v7i2.5529. DOI: https://doi.org/10.30595/juita.v7i2.5529
I. Journal, “Komparasi Teknik Klasifikasi Teks Mining Pada Analisis Sentimen,” J. Netw. Secur. -, vol. 6, no. 1, pp. 28–36, 2017.
I. T. Julianto, D. Kurniadi, and B. B. Balilo Jr, “Enhancing Sentiment Analysis with Chatbots: A Comparative Study of Text Pre-Processing,” J. Tek. Inform., vol. 4, no. 6, pp. 1419–1430, 2023. DOI: https://doi.org/10.52436/1.jutif.2023.4.6.1448
Hanadian Nurhayati-Wolff, “Market Share of E-commerce Platforms in Indonesia 2023,” statista.
Z. Zhan, “Comparative Analysis of TF-IDF and Word2Vec in Sentiment Analysis : A Case of Food Reviews,” vol. 02013, 2025. DOI: https://doi.org/10.1051/itmconf/20257002013
A. Azis Maarif, “Penerapan Algoritma Tf-Idf Untuk Pencarian Karya Ilmiah,” Univ. Dian Nusant., 2015.
F. Sains, D. A. N. Teknologi, U. Islam, N. Sultan, and S. Kasim, “Data Persediaan Barang Menggunakan Metode Elbow Dan K-Medoid Tugas Akhir,” 2024.
H. Nababan, I. Kelana Jaya, S. Manurung, and H. Artikel, “Analisis Sentimen Produk Penjualan Shopee Pada Pengguna Twitter Menggunakan Metode K-Means,” J. Ilm. Sist. Inf., vol. 3, no. 2, pp. 137–142, 2023.
D. P. Langgeni, Z. K. A. Baizal, and Y. F. A. W, “Clustering Artikel Berita Berbahasa Indonesia Menggunakan Unsupervised Feature Selection,” Semin. Nas. Inform. 2010, vol. 2010, no. semnasIF, pp. 1–10, 2010.
G. N. M. Nata, I. Bagiarta, I. P. Ramayasa, and ..., “Pengembangan Algoritma Stemmer Bilingual Bali-Indonesia Dengan Rule-Base,” Pros. …, pp. 278–283, 2023.
I. T. Julianto and D. S. Nurpajar, “User Sentiment Analysis X Towards Makan Bergizi Gratis Program Using Automatic Labeling Technique with Deepseek AI,” J. Intell. Syst. Technol. Informatics, vol. 1, no. 2, pp. 37–44, Sep. 2025, doi: 10.64878/jistics.v1i2.43. DOI: https://doi.org/10.64878/jistics.v1i2.43
N. F. Permatasari, “Pengelompokan Kategori Tweet terhadap Penggunaan E-Wallet di Indonesia Menggunakan Metode K-Means dan Latent Dirichlet Allocation (LDA),” 2019.
M. M. J. Adnan, M. L. Hemmje, and M. A. Kaufmann, “Social Media Mining to Study Social User Group by Visualizing Tweet Clusters using Word2Vec, PCA and K-Means.,” in BIRDS+ WEPIR@ CHIIR, 2021, pp. 40–51.
R. Ishak and A. Bengnga, “Clustering Prestasi Akademik Lulusan Menggunakan Metode K-Means,” Jambura J. Electr. Electron. Eng., vol. 6, no. 1, pp. 76–81, 2024, doi: 10.37905/jjeee.v6i1.23967. DOI: https://doi.org/10.37905/jjeee.v6i1.23967
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2025 Gilang Arbiansyah, Faizal Haq
This work is licensed under a Creative Commons Attribution 4.0 International License.
License:
This is an open-access article distributed under the terms of the Creative Commons Attribution 4.0 International License (CC BY 4.0), which permits unrestricted use, distribution, and reproduction in any medium, provided the original author(s) and source are credited.
