Sexism in the lyrics of the most listened to songs in Spain

This repository contains code and data for an ongoing research project on sexism in music lyrics. The research analyzed the lyrics of more than two thousand songs released throughout a period of about six decades (1960-2022). We used automatic text classification based on manually labeled training data to categorize music lyrics as sexist or non-sexist, while detecting broad categories of sexist speech present in them. We also considered whether the lyrics contained racialized speech. The main findings show that sexism has been prevalent during the observation period, and has increased considerably over the last decade.