Automatically Detecting Cyberbullying Comments on Online Game Forums

TL;DR

This paper presents a machine learning approach using Toxic-BERT to automatically detect cyberbullying comments in online game forums, achieving over 82% F1-score on datasets from WoW and LoL.

Contribution

It introduces a novel application of Toxic-BERT for cyberbullying detection in gaming forums with high accuracy.

Findings

Achieved 82.69% macro F1-score on LoL dataset.

Achieved 83.86% macro F1-score on WoW dataset.

Demonstrated effectiveness of Toxic-BERT in this domain.

Abstract

Online game forums are popular to most of game players. They use it to communicate and discuss the strategy of the game, or even to make friends. However, game forums also contain abusive and harassment speech, disturbing and threatening players. Therefore, it is necessary to automatically detect and remove cyberbullying comments to keep the game forum clean and friendly. We use the Cyberbullying dataset collected from World of Warcraft (WoW) and League of Legends (LoL) forums and train classification models to automatically detect whether a comment of a player is abusive or not. The result obtains 82.69% of macro F1-score for LoL forum and 83.86% of macro F1-score for WoW forum by the Toxic-BERT model on the Cyberbullying dataset.