The increasing popularity of skincare products in Indonesia has encouraged many consumers to seek and share information through online platforms. One of the most influential platforms is Female Daily, which provides a space for users to review and discuss various skincare products. This study aims to explore the dominant topics within user-generated comments related to skincare products on Female Daily. The research employed a descriptive qualitative approach using topic modeling with Latent Dirichlet Allocation (LDA). Data were collected from user comments on several popular skincare products and were preprocessed through punctuation removal, case folding, tokenization, normalization, stopword removal, and stemming. The optimal number of topics was determined using coherence scores. The results reveal that users frequently discuss personal experiences, highlight product benefits and drawbacks, and often refer to their specific skin concerns. These insights provide valuable information for skincare brands to understand customer preferences and perceptions. In conclusion, topic modeling with LDA proves effective in extracting meaningful themes from large-scale textual data, offering a useful method for analyzing consumer feedback in the beauty industry.
Nabila et al. (Tue,) studied this question.