Semantics derived automatically from language corpora contain human-like biases

Aylin Caliskan, Joanna J Bryson, Arvind Narayanan

Research output: Contribution to journalArticlepeer-review

490 Citations (SciVal)
5672 Downloads (Pure)


Machine learning is a means to derive artificial intelligence by discovering patterns in existing data. Here, we show that applying machine learning to ordinary human language results in human-like semantic biases. We replicated a spectrum of known biases, as measured by the Implicit Association Test, using a widely used, purely statistical machine-learning model trained on a standard corpus of text from the World Wide Web. Our results indicate that text corpora contain recoverable and accurate imprints of our historic biases, whether morally neutral as toward insects or flowers, problematic as toward race or gender, or even simply veridical, reflecting the status quo distribution of gender with respect to careers or first names. Our methods hold promise for identifying and addressing sources of bias in culture, including technology.
Original languageEnglish
Pages (from-to)183-186
Number of pages4
Issue number6334
Early online date14 Apr 2017
Publication statusPublished - 14 Apr 2017


  • cs.AI
  • cs.CL
  • cs.CY
  • cs.LG


Dive into the research topics of 'Semantics derived automatically from language corpora contain human-like biases'. Together they form a unique fingerprint.

Cite this