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

Lifetime honour for former Provost

Professor Barry Everitt, former Provost of the Gates Cambridge Trust, has been elected a lifetime Fellow of the American Association for the Advancement of Science (AAAS) the world’s largest general scientific society and publisher of the Science family of journals. AAAS has elected more than 500 scientists, engineers and innovators from around the world and […]

‘Tackle climate change misinformation through computational social science’

Future leaders and researchers need to be urgently trained to tackle climate change misinformation through an interdisciplinary approach that foregrounds computational social science and extends beyond laboratories and university campuses to shape the science-policy interface and rebuild public trust in climate research, according to leading academics. Writing in Nature Human Behaviour, the academics, including Dr Ramit […]

An existential psychological thriller for aesthetes

Christy Edwall’s first novel, History Keeps Me Awake at Night, out in early February, has been described as “an existential psychological thriller for aesthetes and lovers of cultural London and the world… A story cleverly told of a young woman involved in contemporary forms of global voyeurism”. It tells the story of Margit, a London […]

A detective of ancient climate change

Stijn De Schepper is an ancient detective. His job is to investigate past climate change through working his way down the ocean bed, starting with today’s sediment and moving back through thousands of years of Earth’s history.  He maps ancient marine sediments to find out if, why and how the environment changed in the past. […]