FITNet: Identifying Fashion Influencers on Twitter

要旨

The rise of social media has changed the nature of the fashion industry. Influence is no longer concentrated in the hands of an elite few: social networks have distributed power across a broader set of tastemakers. To understand this new landscape of influence, we created FITNet --- a network of 10,000 fashion-related Twitter accounts that heavily influence the larger Twitter fashion graph. To construct FITNet, we trained a content-based classifier to predict which accounts are related to fashion. Leveraging this classifier, we estimated the size of Twitter's fashion subgraph, snowball sampled more than 300k fashion-related accounts based on following relationships, and identified the top 10,000 influencers, or FITNet, in the resulting subgraph. We asked 55 fashion undergraduates to validate and further categorize the accounts in FITNet. These categorizations allow us to analyze interactions between influential people, brands, retailers, and media in fashion.

著者
Jinda Han
University of Illinois at Urbana Champaign, Urbana, Illinois, United States
Qinglin Chen
University of Illinois at Urbana Champaign, Urbana, Illinois, United States
Xilun Jin
University of Illinois at Urbana-Champaign, Urbana, Illinois, United States
Weikai Xu
University of Illinois Urbana-Champaign, Champaign, Illinois, United States
Wanxian Yang
University of Illinois at Urbana-Champaign, Urbana, Illinois, United States
Suhansanu Kumar
University of Illinois at Urbana Champaign, Urbana, Illinois, United States
Li Zhao
University of Missouri, Columbia, Missouri, United States
Hari Sundaram
Ranjitha Kumar
University of Illinois at Urbana-Champaign, Urbana, Illinois, United States
論文URL

https://doi.org/10.1145/3449227

動画

会議: CSCW2021

The 24th ACM Conference on Computer-Supported Cooperative Work and Social Computing

セッション: Social Media

Papers Room A
8 件の発表
2021-10-27 20:30:00
2021-10-27 22:00:00