Approaching fashion design trend applications using text mining and semantic network analysis

Abstract

This study aims to identify fashion trends with design features and provide a consumer-driven fashion design application in digital dynamics, by using text mining and semantic network analysis. We examined the current role and approach of fashion forecasting and developed a trend analysis process using consumer text data. This study focuses on analyzing blog posts regarding fashion collections. Specifically, we chose the jacket as our fashion item to produce practical results for our trend report, as it is an item used in multiple seasons and can be representative of fashion as a whole. We collected 29,436 blog posts from the past decade that included the keywords “jacket” and “fashion collection.” After the data collection, we established a list of fashion trend words for each design feature by classifying styles (e.g., retro), colors (e.g., black), fabrics (e.g., leather), and patterns (e.g., checkered). A time-series cluster analysis was used to categorize fashion trends into four clusters—increasing, decreasing, evergreen, and seasonal trends—and a semantic network analysis visualized the latest season’s dominant trends along with their corresponding design features. We concluded that these results are useful as they can reduce the time-consuming process of fashion trend analysis and offer consumer-driven fashion design guidelines.

Semantic Network Analysis to Explore the Concept of Sustainability in the Apparel and Textile Industry

“…Consumers actively participate in various social media platforms to exchange their thoughts, opinions, and information about fashion purchases and consumption [60]. Recently, the number of meaningful network studies using big data of social media has increased due to the advantage of obtaining more customer-centered and in-depth information compared to the results derived from surveys or interviews with consumers [21,61,62]. Big data refers to large-scale data including unstructured data, such as text and video data, as well as large-scale, digitized data generated within digital environments such as the Internet and SNS [61].…”

“…As a result, there have been many changes in the data and analysis methods used in research [51]. Many programs have been used to collect, analyze, and visualize data on social media with numerous ways to present the results [61,62]. Furthermore, research using big data analysis methods shows that the scope of research has expanded both quantitatively and qualitatively beyond the limitations of the small number of people in the study and the boundaries of accessibility to survey responses [22].…”

“…Given that new informatics techniques are considered an advanced approach to investigate the segmented fashion market (i.e., sustainable fashion market), the fashion industry has used SNS data to understand and forecast fashion consumers' behavior [63]. Text mining, a method to extract extensive knowledge from unstructured text in SNS, has been conducted using natural language processing, a form of machine learning that takes massive amounts of language text and converts it into a useful form for researchers or practitioners by mining and extracting important keywords [62,64]. Semantic network analysis reveals knowledge and information about semantic networks between words in a network by demonstrating the information in a visual graph with labeled nodes [61].…”

“…Semantic network analysis reveals knowledge and information about semantic networks between words in a network by demonstrating the information in a visual graph with labeled nodes [61]. Principally, any words in semantic networks that may be related to other words can be deemed nodes [62].…”

“…A few studies have explored the potential application of semantic network analysis in fashion research. An and Park [62] incorporated text mining and semantic network analysis into the fashion trend analysis process to analyze fashion collections using social media applications. Kim et al [24] also identified top actors leading the green consumption network (i.e., eBay Green Team Facebook) and characterized keywords/word-pairs as user messages.…”