Quantifying Gender Bias in Consumer Culture
This addresses the problem of measuring subtle cultural biases for researchers and policymakers, though it is incremental in applying existing NLP methods to new data.
The study quantified gender bias in song lyrics over 50 years using NLP on 250,000 songs, finding that women are less associated with desirable traits like competence, with bias decreasing but persisting over time.
Cultural items like songs have an important impact in creating and reinforcing stereotypes, biases, and discrimination. But the actual nature of such items is often less transparent. Take songs, for example. Are lyrics biased against women? And how have any such biases changed over time? Natural language processing of a quarter of a million songs over 50 years quantifies misogyny. Women are less likely to be associated with desirable traits (i.e., competence), and while this bias has decreased, it persists. Ancillary analyses further suggest that song lyrics may help drive shifts in societal stereotypes towards women, and that lyrical shifts are driven by male artists (as female artists were less biased to begin with). Overall, these results shed light on cultural evolution, subtle measures of bias and discrimination, and how natural language processing and machine learning can provide deeper insight into stereotypes and cultural change.