|
KMID : 1145120210190020263
|
|
Asian Journal of Beauty and Cosmetology
2021 Volume.19 No. 2 p.263 ~ p.275
|
|
|
What Semiotic Values Do Cosmetics Consumers Consume?: Analysis of Cosmetic Brand Reputation and Brand Selection Attributes Using Text Mining
|
|
Song Man-Seok
|
|
|
Abstract
|
|
|
Purpose: This study aims to empirically analyze how consumers perceive their consumption of the semiotic value from cosmetics that they purchased by using text-mining analysis techniques-word cloud analysis, semantic network analysis, and sensitivity analysis-and examining the subjective emotional big data that consumers have left as discourse reviews concerning the brand reputation and selection attributes of cosmetics in social media.
Methods: R version 3.6.2-RStudio Version 1.4.1103 was used to collect and analyze the review data on the semiotic value experience that cosmetics consumers left after their purchases. The research was conducted in three stages: the pre-processing of collected data and setting of stopwords, the execution of modeling, and the result analysis.
Results: The word cloud analysis evinced that the word “skin” appeared the most, followed by “purchase” and “nature”. The fact that such keywords featured prominently suggests that cosmetics consumers described their experience of their purchased cosmetics based on a semiotic value. The semantic network analysis revealed that “nature”, “product”, “real,” “cover,” “use,” and “skin cosmetics” had high levels of degree centrality, betweenness centrality, and closeness centrality. Finally, through the sensitivity analysis, 4,742 words showing positive reviews, 2,039 words showing negative reviews, and 14,146 showing neutral reviews were found.
Conclusion: In the word cloud analysis, the top 30 keywords represented the purchase goal and selection attribute of cosmetics consumers well and are considerably important for consumption factors related to cosmetics. “Real”, “product”, and “skin cosmetics”, all of which were high in betweenness centrality, degree centrality, and closeness centrality in the semantic network analysis, play an important role in spreading and connecting “meaning” toward particular cosmetics brands on a daily basis. Finally, the sensitivity analysis found that positive emotional reviews appeared approximately 2.33 times more often than negative ones.
|
|
|
KEYWORD
|
|
|
Semiotic value, Text mining, Word cloud analysis, Semantic network analysis, Sensitivity analysis
|
|
|
FullTexts / Linksout information
|
|
|
|
|
|
Listed journal information
|
|
|
|
|