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

Tracing the origins of our political beliefs

What makes some people more vulnerable to extremism than others? How do we build cognitive resilience against extreme ideologies? And how does the brain react to misinformation on social media? These are some of the key political questions that political neuroscientist Leor Zmigrod [2016] is exploring, putting the science into our understanding of radicalisation.   Leor […]

A leading woman in STEAM

A Gates Cambridge Scholar has been selected as one of the 75 leading women in Science, Technology, Engineering, Arts and Mathematics in India. Yama Dixit will feature in the second edition of the book She Is, published by the Red Dot Foundation in partnership with the Office of the Principal Scientific Adviser, Government of India to mark 75 […]

Tackling the obesity epidemic in Africa

When she left school, Paula-Peace James-Okoro [2022] intended to become a medical doctor, but after starting a degree in Biochemistry she discovered a passion for the subject and for using it to address one of the major health challenges facing Africa – obesity. She says: “In Africa, the rates of metabolic diseases, like obesity and […]

Triple win for Bill Gates Sr. Prize

For the first time three Gates Cambridge Scholars are sharing this year’s Bill Gates Sr. Prize in recognition of their outstanding research and social leadership. Kim van Daalen, Reetika Subramanian and Cynthia Okoye have been selected for the prize which was established by the Gates Cambridge Trustees in June 2012 in recognition of the late […]