They then applied Natural Language Processing (NLP) techniques to subtitles of the films to examine how social biases have evolved over time.<\/p>\n
\u201cOur argument is simple,\u201d the researchers wrote in their study paper<\/a>. \u201cPopular movie content reflects social norms and beliefs in some form or shape.\u201d<\/p>\n [Read: <\/i>How do you build a pet-friendly gadget? We asked experts and animal owners<\/i><\/span><\/a>]<\/i><\/span><\/p>\n The researchers investigated depictions of beauty in the movies by using a fill-in-the-blank assessment known as a cloze test.<\/p>\n They trained a language model on the movie subtitles, and then set it to complete the following sentence:<\/p>\n A beautiful woman should have [MASK] skin.<\/p>\n<\/blockquote>\n While the base model they used predicted \u201csoft\u201d as the answer, their fine-tuned version consistently selected the word \u201cfair.\u201d<\/p>\n The same thing happened when the model was trained on Hollywood subtitles, although the bias was less pronounced.<\/p>\n The researchers attribute the difference to \u201cthe age-old affinity toward lighter skin in Indian culture.\u201d<\/p>\n The study also evaluated the prevalence of female characters in films by comparing the number of gendered pronouns in the subtitles.<\/p>\n The results indicate that the progress towards gender parity in both Hollywood and Bollywood has been slow and fluctuating<\/p>\n The male pronoun ratio in both film industries had dipped far less over time than a selection of Google Books. The researchers also analyzed sentiments about dowry in India since it became illegal in 1961 by analyzing the vocabulary with which it was it was connected in the films.<\/p>\n They found words including \u201cloan,\u201d \u201cdebt,\u201d and \u201cjewelry\u201d in movies of the 1950s, suggesting compliance with the practice. But by the 2000s, the words most closely associated with dowry were more negative examples, such as \u201ctrouble,\u201d \u201cdivorce,\u201d and \u201crefused,\u201d indicating non-compliance or more gloomy consequences.<\/p>\n \u201cAll of these things we kind of knew, but now we have numbers to quantify them,\u201d said study co-author Ashiqur R. KhudaBukhsh. \u201c<\/span>And we can also see the progress over the last 70 years as these biases have been reduced.\u201d<\/p>\n The study shows that NLP can uncover how popular culture reflects social biases. The next step could be using the tech to show how popular culture influences those biases.<\/p>\n Published February 25, 2021 \u2014 21:05 UTC <\/p>\n\n
Evolving trends<\/h2>\n
![\"The](\"https:\/\/cdn0.tnwcdn.com\/wp-content\/blogs.dir\/1\/files\/2021\/02\/Screenshot-2021-02-25-at-19.28.19.png\")