Towards Detecting Contextual Real-Time Toxicity for In-Game Chat

Zachary Yang, Nicolas Grenan-Godbout, Reihaneh Rabbany
10/20/2023
cs.CLcs.AIcs.LG

No official code found. Best implementation: ubisoft/ubisoft-laforge-toxbuster (7 stars, last commit 2023-06-27).

Abstract

Real-time toxicity detection in online environments poses a significant challenge, due to the increasing prevalence of social media and gaming platforms. We introduce ToxBuster, a simple and scalable model that reliably detects toxic content in real-time for a line of chat by including chat history and metadata. ToxBuster consistently outperforms conventional toxicity models across popular multiplayer games, including Rainbow Six Siege, For Honor, and DOTA 2. We conduct an ablation study to assess the importance of each model component and explore ToxBuster's transferability across the datasets. Furthermore, we showcase ToxBuster's efficacy in post-game moderation, successfully flagging 82.1% of chat-reported players at a precision level of 90.0%. Additionally, we show how an additional 6% of unreported toxic players can be proactively moderated.

View on arXivView PDF

Code Implementations(1)

ubisoft/ubisoft-laforge-toxbusterCommunity100%

Using Language Models to Identify and Classify Toxicity Inside In-Game Chat

71Python, BatchfileJun 27, 20233 years agoNOASSERTION
toxicity-classificationtoxicity-detection

Similar Papers

ToxBuster: In-game Chat Toxicity Buster with BERT

92% match2023

ToxicChat: Unveiling Hidden Challenges of Toxicity Detection in Real-World User-AI Conversation

86% match2023

Context-Aware Toxicity Detection in Multiplayer Games: Integrating Domain-Adaptive Pretraining and Match Metadata

86% match1 repo12025

Unified Game Moderation: Soft-Prompting and LLM-Assisted Label Transfer for Resource-Efficient Toxicity Detection

85% match2025

Fine-Tuning Pre-trained Language Models to Detect In-Game Trash Talks

84% match2024

Efficient Toxicity Detection in Gaming Chats: A Comparative Study of Embeddings, Fine-Tuned Transformers and LLMs

84% match2025

Cite this paper

@article{yang2023towards,
  title  = {Towards Detecting Contextual Real-Time Toxicity for In-Game Chat},
  author = {Zachary Yang and Nicolas Grenan-Godbout and Reihaneh Rabbany},
  year   = {2023},
  eprint = {2310.18330},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2310.18330v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2310.18330.svg)](https://codeofpaper.com/paper/2310.18330)

Discussion