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.
- Department of Computer Science - Reader
- Centre for Networks and Collective Behaviour
- Institute for Policy Research (IPR)
- Centre for Mathematical Biology
- UKRI CDT in Accountable, Responsible and Transparent AI
- Centre for Autonomous Robotics (CENTAUR)
Person: Research & Teaching