Electronic 'word of mouth' useful in detecting, predicting fashion trends

Data analytics are impacting all kinds of business, including the fashion industry. Li Zhao, assistant professor of textile apparel management in the College of Human Environmental Sciences, has now found that social media data can help fashion companies discover how communities are connected to their brands. This can help them determine upcoming trends and if celebrity endorsements are having the desired impact.

"We know that people talk and are interested in fashion, so it makes sense that they talk about it on social media," Zhao said. "The data presented in this study show that designers should listen to what they are saying about trends on social media."

Zhao and co-author Chao Min, a researcher at Nanjing University in China, created a series of social networks based on hashtags people used on Twitter before, during and after Paris Fashion Week. Social networks are a way to understand the relationships or links between distinct social media content - users, sentiment and ideas.

By searching for tweets featuring #ParisFashionWeek and #PFW, the researchers were able to find relevant social media content. They used the tweets to create social networks. For example, Zhao found tweets about hand embroidery connected to tweets about Fashion Week, establishing an association between the technique and users interested in haute couture. Other keywords related to couture emerged within the social networks, such as #handmade, #elegant and #art.

Zhao also was able to tell how celebrities were influencing brands based on the social networks. Kristen Stewart and Katy Perry were two celebrities that showed a large influence for the Chanel brand during Fashion Week, giving Zhao reason to believe that the two celebrities are effective influencers for the brand.

"Consumers are using 'electronic word of mouth' during Paris Fashion Week and other major fashion events." Zhao said. "Fashion researchers and designers can listen to what they are saying to understand the direction of fashion trends and to understand how consumers are engaging with fashion brands."

"The rise of fashion informatics: a case of data-mining based social network analysis in fashion," recently was published in the Clothing and Textiles Research Journal. In future research, Zhao hopes to investigate how social media users with different geographical locations discuss the same fashion event.