Are computer algorithms sexist?

  • August 8, 2016
Are computer algorithms sexist?

James Yang Zou co-authors paper which attempts to counter inherent sexism in computer algorithms.

By reducing the bias in today’s computer systems (or at least not amplifying the bias), which is increasingly reliant on word embeddings, in a small way debiased word embeddings can hopefully contribute to reducing gender bias in society.

James Yang Zou and colleagues

Are computer algorithms inherently sexist and if so what can be done about it? A research paper co-authored by a Gates Cambridge Scholar shows how data sets embed sexist assumptions into searches and investigates how to counter this.

The paper, Man is to Computer Programmer as Woman is to Homemaker? Debiasing Word Embeddings, is published in arXiv.org. Led by Tolga Bolukbasi  from Boston University and co-authored by Gates Cambridge Scholar James Yang Zou [2007], who is currently an assistant professor at Stanford University, it investigates patterns in the way words on the internet appear next to each other based on a powerful data set called Word2vec devised by Google researchers researching Google News.

But the new study finds vector space is blatantly sexist with embedded pairings including she:he :midwife:doctor; sewing:carpentry; registered_nurse:physician; whore:coward; hairdresser:barber; nude:shirtless; boobs:ass; giggling:grinning; and nanny:chauffeur. This occurs because any bias in the Google News articles that make up the Word2vec corpus is captured in the geometry of the vector space.  They are concerned at the role of vector space in web searches, for instance, it could affect searches for potential candidates for jobs in professions deemed more "male" such as computer programming. The researchers says this could have the effect of increasing bias, rather than simply reflecting it.

To counter this, they use standard mathematical tools to manipulate vector space. That involves searching the vector space using Amazon's Mechanical Turk to find whether embedded pairings are appropriate or inappropriate.

After compiling a list of gender biased pairs, the team subjected it to a process of "hard de-biasing", with the sexist bias removed from the vector space. The pairings were then subject to the Mechanical Turk again and both direct and indirect bias was significantly reduced.

“One perspective on bias in word embeddings is that it merely reflects bias in society, and therefore one should attempt to debias society rather than word embeddings,” say the researchers. “However, by reducing the bias in today’s computer systems (or at least not amplifying the bias), which is increasingly reliant on word embeddings, in a small way debiased word embeddings can hopefully contribute to reducing gender bias in society…At the very least, machine learning should not be used to inadvertently amplify these biases.”

*Picture credit: Wikipedia.

James Zou

James Zou

  • Alumni
  • United States
  • 2007 CASM Applied Mathematics
  • Jesus College

I am participating in the Part III program in Applied Mathematics at Cambridge. I'm interested in the quantitative aspects of a wide range of topics--biology, sociology, and AI. I hope to explore the synthesis of these diverse topics at a fundamental level. I look forward to completing a Ph.D. after Part III.

Latest News

Addressing energy injustice in the Global South

A new framework which uses artificial intelligence to analyse textual data on energy use and behaviour could help policymakers develop a deeper understanding of energy injustices in the Global South. The study, Grounded reality meets machine learning: A deep-narrative analysis framework for energy policy research, was led by Gates Cambridge Scholar Ramit Debnath [2018] and is published in the journal Energy Research […]

Scholar wins top German prize for PhD thesis

A Gates Cambridge Scholar has won a prestigious international award for her PhD dissertation on the relationship between offshore finance and state power. Dr Andrea Binder was named winner of the Körber Foundation’s German Dissertation Award 2020 for social sciences. The prize, one of the most highly endowed for young researchers from Germany, honours excellent PhD research which […]

Developing a farm for impact model

Shadrack Frimpong has not yet started his PhD, but already his and his team’s work has earned him awards from the Queen, the Clinton Foundation and the Muhammad Ali Foundation. The awards are for their outstanding work in creating a potential new development model for rural crop-growing communities starting from Shadrack’s own village in Ghana. […]

An interdisciplinary approach to major global challenges

Midway through her PhD at Cambridge Molly Crockett and her team discovered a critical role for the neurotransmitter serotonin in regulating social decision-making. “We found that temporarily disrupting serotonin levels made people more willing to punish unfairness,” says Molly. “I had come to Cambridge planning to look at how serotonin affects self-regulation in a broad sense, but […]