Article Per Year (5 Year)
p-Index From 2021 - 2026
0.23
P-Index
This Author published in this journals
All Journal Inform : Jurnal Ilmiah Bidang Teknologi Informasi dan Komunikasi
R Fenny Syafariani
Information System Departement, Universitas Komputer Indonesia, Bandung, Indonesia
Computer Science & IT Control & Systems Engineering Electrical & Electronics Engineering Engineering Library & Information Science

Published : 1 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 1 Documents
Search

 1 
Mapping Skincare Consumer Preferences with Data Mining: Evidence from Emerging Market Trends Novrini Hasti; Andri Sahata Sitanggang; R Fenny Syafariani; Febilita Wulan Sari; Imelda Pangaribuan; Sussy Susanti
Inform : Jurnal Ilmiah Bidang Teknologi Informasi dan Komunikasi Vol. 11 No. 2 (2026)
Publisher : Universitas Dr. Soetomo

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.25139/inform.v11i2.11825

Abstract

Indonesia’s growing digital economy has reshaped how consumers search for and compare skincare products online. Prior studies often examine beauty-related search behavior using single-source or static approaches. This study analyzes skincare consumer preferences in Indonesia using Google Trends data from January 2020 to August 2025 for five keywords: skincare, serum, sunscreen, toner, and moisturizer. To capture the multidimensional nature of online search attention, this study integrates temporal, spatial, relational, clustering, and short-text classification analyses, with Google Trends Related Queries serving as the textual data for classification. The results reveal that skincare interest in Indonesia is dynamic and geographically segmented. Serum reached the highest search index of 100 in December 2020 but then declined, while sunscreen showed a positive trend with recurring seasonal peaks. General skincare searches remained relatively stable, whereas toner showed a gradual decline. Spatial analysis indicates that leading provinces vary by product category, confirming that national search averages may conceal local demand signals. Trend clustering identified two main typologies with moderate separation. At the same time, the classification task showed that Multinomial Naïve Bayes achieved stronger performance than Linear SVM, with an F1 score of 0.78 and an AUC of 0.81. These findings show that search-based data can reveal structured consumer preferences across time, regions, and product categories. The study contributes an interpretable framework for digital consumer analytics and offers practical implications for timing-based campaigns, regional targeting, and skincare market monitoring.
Co-Authors Andri Sahata Sitanggang Febilita Wulan Sari Imelda Pangaribuan Novrini Hasti Sussy Susanti