<![CDATA[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.]]>
Copyrights © 2026
