Uncovering Biased Language Use: Understanding the Communication of Stereotypes in Natural Language

Everyday language use contains many (implicit) expressions about social categories, such as minority, age, and gender groups. Such language contributes to the formation and reinforcement of stereotypes and, often unconsciously, fuels stereotyping and discrimination. In this project, we aim to create a thorough understanding and awareness of stereotypical communication by studying when and how stereotypes are reflected in, and derived from, freely produced natural language. Additionally, we are developing a software toolkit to automatically detect stereotypes and biases in texts. This toolkit can reveal implicit stereotyping in various real-world contexts and enables further (applied) research, monitoring, correction, prevention, and education on stereotyping.

The project ‘Uncovering Biased Language Use: Understanding the Communication of Stereotypes in Natural Language’ is funded by the Dutch Research Council (NWO) in the Open Competition M research programme (Project nr. 406.22.SW.008).