Relating Word Embedding Gender Biases to Gender Gaps: A Cross-Cultural Analysis
This study quantifies gender bias in word embeddings and investigates its association with real-world gender disparities across societies. Leveraging Twitter data from 51 U.S. regions and 99 countries in 2018, the authors construct a metric of gender bias in word embeddings and systematically correlate it with 18 international and 5 U.S.-specific gender gap indicators spanning education, politics, economics, and health. The analysis reveals significant cross-cultural correlations and strong predictive power, demonstrating for the first time that gender bias embedded in language models serves as a valid proxy for societal gender inequality. These findings establish a novel paradigm for monitoring social biases through computational linguistic methods at a global scale.