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

Shaping policy and Alzheimer’s research

Just six years since leaving Cambridge, Brianne Kent has secured a role as Assistant Professor, won multiple awards,  become the first early career researcher on the Governing Council of the Canadian Institutes of Health Research [CIHR] and is currently setting up her own laboratory to further her studies on Alzheimer’s disease. Since January, when she […]

Ed-tech wins Gates Foundation funding for access work

An ed-tech non-profit co-founded by a Gates Cambridge Scholar has received a $980,000 grant from the Bill & Melinda Gates Foundation to develop its free college affordability tool. Moneythink, co-founded by Greg Nance who is also its Board Chair, says the money will help it to accelerate the development and reach of DecidED, its free […]

Gates Cambridge: a purposeful community

As the Gates Cambridge Scholarship reaches the end of its 20th anniversary year, its alumni association is holding an event late this month which celebrates some of the factors that have shaped the scholar community. That sense of community, of a global network of leaders, developed and owned by the scholars and alumni themselves, is […]

Fibre optic project aims to improve Sri Lanka’s infrastructure

A Gates Cambridge Alumnus has formed a partnership between his university, Cambridge and Oxford universities and a local engineering company to introduce a cutting-edge technology to Sri Lanka. A team of researchers and industry experts from the University of Moratuwa in Sri Lanka, the Cambridge Centre for Smart Infrastructure and Construction (CSIC), the University of […]