Researchers using AI technologies have found that male characters are four times more common in literature than female characters.
Mayank Kejriwal from the Viterbi School of Engineering at the University of Southern California drew on work on gender bias and his own work on natural language processing to carry out the experiment.
Kejriwal and fellow researcher Akarsh Nagaraj used data from 3,000 books that are part of Project Gutenberg, in genres including adventure, science fiction, mystery and romance.
The study used named entity recognition (NER) to identify gender-specific characters by looking at things like feminine and masculine pronouns. The researchers also looked at how many female characters were main characters.
“Gender bias is very real, and when you see four times fewer women in literature, it has a subliminal impact on the people who consume the culture,” Kejriwal said. “We quantitatively revealed an indirect way in which prejudice persists in culture.”
But the researchers ran into trouble with those that didn’t fit a binary gender. The AI was unable to determine whether “they” referred to a plural or a “non-dichotomous individual”.
Kejriwal said: “When we published the dataset paper, reviewers criticized that we ignored non-dichotomous genders. But we agreed with them, in a way. We think it’s completely deleted, and we won’t be able to find much [transgender individuals or non-dichotomous individuals].”
In addition to statistics on male and female characters, the researchers also looked at the language associated with gendered characters. Nagaraj said, “Even with misattributions, the words associated with women were adjectives like ‘weak’, ‘lovable’, ‘pretty’ and sometimes ‘stupid’. For the male characters, words describing them included “leadership”, “power”, “strength”, and “politics”.
Kejriwal added: “Our study shows us that the real world is complex but there are benefits for all the different groups in our society who participate in cultural discourse. When we do this, we tend to have a more realistic view of society.