NLP Pipeline for Gender Bias Detection in Portuguese Literature

Abstract

We present a novel Natural Language Processing (NLP) pipeline designed to analyze gender bias in Portuguese literary works. Our pipeline comprises five processing steps, culminating in gender bias detection across different linguistic dimensions. We apply it to a corpus of Portuguese literary texts and evaluate its effectiveness in uncovering gender bias. Our findings reveal prevalent gender stereotypes in character descriptions, with female characters often associated with appearance and emotion, while male characters are depicted in terms of social status and personality traits. Furthermore, our analysis of physical traits stereotypes indicates a more equitable representation across genders in such a dimension.