File photo courtesy: Pixabay.
An analysis of 3.5 million English books published between 1908 and 2008 reveals descriptions of men typically refer to behaviour, while descriptions of women refer to appearance.
‘Righteous’, ‘rational’, and ‘brave’ are more often associated with men. The two most-common adjectives assigned to women are ‘beautiful’ and ‘lovely’.
Scientists used an algorithm to analyze the dataset of books, which included a mix of fiction and non-fiction literature. A total of 11 billion words were scanned.
“We are clearly able to see that the words used for women refer much more to their appearances than the words used to describe men. Thus, we have been able to confirm a widespread perception, only now at a statistical level,” Isabelle Augenstein, a computer scientist and Assistant Professor of the University of Copenhagen’s Department of Computer Science, said in a statement.
Researchers were also able to extract adjectives and verbs associated with gender-specific nouns, like ‘doting daughter’ or ‘proud father’ and analyzed whether they carry positive, negative, or neutral sentiments.
Negative verbs associated with body and appearance were used five times more for females than males.
While several of the books used were published decades ago, Augenstein says the findings are important and have present-day implications.
“If the language we use to describe men and women differs, in employee recommendations, for example, it will influence who is offered a job when companies use IT systems to sort through job applications.”
A research article on the project was recently presented at the 2019 Annual Meeting of the Association for Computational Linguistics.