AI-based Analysis of Bollywood Uncovers the Indian Film Industry's Obsession with 'Fair Skin'

 

For Bollywood, beauty lies in the "fair skin", according to an Artificial Intelligence (AI) -based computer analysis which reveals that conception of beauty has remained consistent through the years in the Indian film industry having its roots in Mumbai.

Bollywood -- the world's largest by number of feature films produced continues, to associate beauty with fair skin, making it one of the many social biases Bollywood has remained consistent with, finds a study led by Indian American researchers at Carnegie Mellon University.

The Indian film industry often known as Bollywood, which is a term for Hindi cinema, a portmanteau of  'Bombay' and 'Hollywood'.

In the study, researchers collected 100 Bollywood movies spanning 70 years, and juxtaposed them against 100 top-grossing Hollywood films made during the same period. They also analyzed subtitles of 1,400 films for gender and social biases in their statistical language models. And finally used artificial intelligence (AI) to make the observation.

The research study alsp revealed that babies whose births were depicted in Bollywood films from the 1950s and ‘60s were more often than not boys; in today's films, boy and girl newborns are about evenly split.

They AI-powered study used a fill-in-the-blank exercise to assess specific statements like "A beautiful woman should have _____ skin". The model predicted ‘fair’ after being trained on Bollywood subtitles data. The bias was less pronounced when the AI model was used on Hollywood subtitles, the team noted.

The team, led by Kunal Khadilkar and Ashiqur KhudaBukhsh of CMU's Language Technologies Institute, used the model to also understand gender diversity in the films. They used ‘Male Pronoun Ratio (MPR)’ metric to compare occurrence of male pronouns with total occurrences of male and female pronouns. Right from 1950 to now, the rate for both Bollywood and Hollywood movies ranged from 60 to 65 MPR, the team noted.

The AI-powered method is said to be able to analyze 2,000 movies in a matter of days, compared with manual cultural studies that can consider up to 10 movies at a time, according to the team.

The tool could also be used to rapidly analyze hundreds of books, magazine articles and social media posts to understand biases that may occur in them, the team said.