Revisiting The Classics: A Study on Identifying and Rectifying Gender Stereotypes in Rhymes and Poems

TL;DR

This paper analyzes gender stereotypes in rhymes and poems, creating a dataset and a model with 97% accuracy to identify bias, and uses LLMs to rectify stereotypes, promoting inclusivity and awareness.

Contribution

It introduces a new dataset and a high-accuracy model for detecting gender stereotypes in literary works, and demonstrates the effectiveness of LLMs in rectifying these biases.

Findings

Model achieves 97% accuracy in identifying gender bias.

LLMs effectively rectify gender stereotypes in literary works.

The study raises awareness about gender bias in poetry and rhymes.

Abstract

Rhymes and poems are a powerful medium for transmitting cultural norms and societal roles. However, the pervasive existence of gender stereotypes in these works perpetuates biased perceptions and limits the scope of individuals' identities. Past works have shown that stereotyping and prejudice emerge in early childhood, and developmental research on causal mechanisms is critical for understanding and controlling stereotyping and prejudice. This work contributes by gathering a dataset of rhymes and poems to identify gender stereotypes and propose a model with 97% accuracy to identify gender bias. Gender stereotypes were rectified using a Large Language Model (LLM) and its effectiveness was evaluated in a comparative survey against human educator rectifications. To summarize, this work highlights the pervasive nature of gender stereotypes in literary works and reveals the potential of LLMs to rectify gender stereotypes. This study raises awareness and promotes inclusivity within artistic expressions, making a significant contribution to the discourse on gender equality.