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

Affecting change for the Māori community

Self-determination lies at the centre of Māori culture. “It’s a way of life,” says Chris Tooley. That idea is also at the heart of his PhD studies at Cambridge and his subsequent work in Parliament and in the community. Chris grew up with a strong sense of being part of the Māori community. He has ancestral […]

On the COVID frontline

Three Gates Cambridge scholars who have been on the medical frontline during the COVID-19 pandemic will be speaking about their experiences at a virtual event next weekend. The event, organised by the Gates Cambridge Alumni Association, will be moderated by Elizabeth Dzeng, Assistant Professor of Medicine at the University of California, San Francisco in the […]

New game tackles Covid conspiracies

A new online game that puts players in the shoes of a purveyor of fake pandemic news is the latest tactic in the UK Government’s efforts to tackle the deluge of coronavirus misinformation that is misleading many and costing lives across the world. Launched to the public today, the Go Viral! game has been developed by the […]

“Democracy does not work on a ‘trust me’ basis”

When Jennifer Gibson started her MPhil at Cambridge in 2001 as part of the inaugural class of Gates Scholars, no-one knew what it meant to be a Gates Cambridge Scholar. Twenty years later, Jennifer is now a human rights lawyer focused on national security issues, something she never could have anticipated, but which she credits in no small part […]