Detecting LGBTQ+ Instances of Cyberbullying

TL;DR

This paper evaluates transformer-based machine learning models to improve the detection of cyberbullying targeting LGBTQ+ individuals on social media, addressing a critical mental health concern.

Contribution

It compares the effectiveness of various transformer models in identifying subtle and complex cyberbullying incidents against LGBTQ+ users using real social media data.

Findings

Transformer models show varying accuracy in detecting LGBTQ+ cyberbullying.

Certain models outperform others in identifying subtle harassment.

The study highlights challenges in detecting nuanced cyberbullying language.

Abstract

Social media continues to have an impact on the trajectory of humanity. However, its introduction has also weaponized keyboards, allowing the abusive language normally reserved for in-person bullying to jump onto the screen, i.e., cyberbullying. Cyberbullying poses a significant threat to adolescents globally, affecting the mental health and well-being of many. A group that is particularly at risk is the LGBTQ+ community, as researchers have uncovered a strong correlation between identifying as LGBTQ+ and suffering from greater online harassment. Therefore, it is critical to develop machine learning models that can accurately discern cyberbullying incidents as they happen to LGBTQ+ members. The aim of this study is to compare the efficacy of several transformer models in identifying cyberbullying targeting LGBTQ+ individuals. We seek to determine the relative merits and demerits of these existing methods in addressing complex and subtle kinds of cyberbullying by assessing their effectiveness with real social media data.