Analyzing Cosmetic Reviews on Social Media Platforms

Abstract

Customers utilize reviews as a valuable source of information when selecting cosmetic products, and reviews significantly influence social media platforms in marketing. This study analyzes the characteristics of cosmetic customer reviews and their effects on sales ranking. This study vectorized cosmetic reviews obtained from X (Twitter) using BERT and conducted hierarchi cal clustering with dimensionality reduction vectors. Analyzing each of the cluster's Word Clouds, we revealed characteristics of clusters along two axes: "product features and information - impre ssions and experiences" and "purchase reports - difficulty in purchasing reports." However, we could not observe a significant correlation between these characteristics and product rankings.