Nav

The Algorithm of Instagram Fashion

By Charissa Echavez | Sep 10, 2015 06:31 PM EDT

A group of researchers from Indiana University (IU) has revealed the possibility of predicting the next top model through utilizing a computational method and data from Instagram. And this computation reputedly claims to be 80 percent accurate.

A number of fashion models from the Fashion Model Directory (FMD) were gathered by the IU scientists using a database. Data were collected in fall 2014. They studied various attributes including hip and waistlines, height, dress and shoe sizes, runways walked, agency, and eye color. The number of runways walked was considered to gauge "popularity" in which a new model participated during the Fall/Winter 2015 season in March.

Accounts of the models on Instagram were scrutinized asserting each user based on the number of followers, number of posts per month, number of "likes", number of "likes" and comments from those posts, and whether the comments were positive or negative.

To test predictability, they circumscribe their attention from 400 to 15 models listed as "new faces" in the FMD. Six of the eight models predicted to achieve popularity were accurately identified. And six out of seven who obtained the lowest score in popularity were also identified precisely.

For the Fall/Winter 2015 season, Sofia Tesmenitskaya, Arina Levchenko, Renata Scheffer, Sasha Antonowskaia, Melanie Culley and Phillipa Hemphrey were the six new models.

"Our analysis suggests that Instagram is as important as being cast by a top agency in terms of its ability to predict success on the runway," said Emilio Ferrara, a computer scientist at the University of Southern California who conducted the research at the IU Bloomignton School of Informatics and Computing's Center for Complex Networks and Systems Research and as a member of the IU Network Science Institute.

"Our framework successfully predicts most of the new popular models who appeared in 2015," Ferrara said. Upon analyzing these models' Instagram accounts, researchers suggest that there is a certain trend. They found that factors of success include a high number of likes and comments as well as frequent posting.

"Social media is changing the game dramatically. Traditionally, models don't interact with consumers; but now their online activity plays an important role in popularity and ultimately, success," said Giovanni Luca Ciampaglia, a postdoctoral researcher at the Center for Complex Networks and Systems Research, who is also an IU contributor.

Latest Stories