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

Towards a dictionary of the human genome

Marie Brunet’s research focuses on the secrets still hidden in our genomes. She says that despite the fact that we live in an era where getting our genome sequenced is possible, we still don’t know the origin of two fifths of inherited diseases. That is because, as she says, the genome only currently maps the […]

Scholar recognised for research into misinformation

A Gates Cambridge Scholar has been shortlisted for a Women of the Future Award for her research into countering misinformation. Melisa Basol [2018] was shortlisted for the science category of the UK Awards which recognises “truly remarkable female scientists, forging new ground in research and scientific achievement”. There are 11 other categories and three special […]

Scholars join forces on anti-cancer drug

Two Gates Cambridge Scholars have joined forces to work on a drug candidate that has the potential to replace one of the most widely used cancer drugs around the world. Dr Anand Jeyasekharan [2004], who did his PhD in Oncology, and Dr Chandler Robinson [2009] who did an MBA at Cambridge, will collaborate on a […]

Making the experiences of imprisoned women activists visible

Growing up in a small town in Bengal, Jigisha Bhattacharya [2022] developed a particular sensitivity to marginalised groups and conflicts between different communities and identities from an early age.  It is this interest and her experience of political protests at university, combined with a longstanding curiosity about the links between politics and the arts, that […]