Image de couverture de livre

Toxicity in Twitch Chats: An LLM-Based Analysis Across Gaming Communities

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Fuchs, Ronja, Rupp, Florian, Bertram, Timo, Eckert, Kai, Dockhorn, Alexander
Format:	Preprint
Publié:	2026
Sujets:	Computation and Language
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

GEEvo: Game Economy Generation and Balancing with Evolutionary Algorithms
par: Rupp, Florian, et autres
Publié: (2024)

Deceptive Game Design? Investigating the Impact of Visual Card Style on Player Perception
par: Kallabis, Leonie, et autres
Publié: (2025)

Analyzing Pokémon and Mario Streamers' Twitch Chat with LLM-based User Embeddings
par: Hämäläinen, Mika, et autres
Publié: (2024)

Balancing of competitive two-player Game Levels with Reinforcement Learning
par: Rupp, Florian, et autres
Publié: (2023)

Personalized Dynamic Difficulty Adjustment -- Imitation Learning Meets Reinforcement Learning
par: Fuchs, Ronja, et autres
Publié: (2024)

Level the Level: Balancing Game Levels for Asymmetric Player Archetypes With Reinforcement Learning
par: Rupp, Florian, et autres
Publié: (2025)

It might be balanced, but is it actually good? An Empirical Evaluation of Game Level Balancing
par: Rupp, Florian, et autres
Publié: (2024)

Towards Detecting Contextual Real-Time Toxicity for In-Game Chat
par: Yang, Zachary, et autres
Publié: (2023)

Simulation-Driven Balancing of Competitive Game Levels with Reinforcement Learning
par: Rupp, Florian, et autres
Publié: (2025)

G-PCGRL: Procedural Graph Data Generation via Reinforcement Learning
par: Rupp, Florian, et autres
Publié: (2024)

Dialectal Toxicity Detection: Evaluating LLM-as-a-Judge Consistency Across Language Varieties
par: Faisal, Fahim, et autres
Publié: (2024)

Silencing Empowerment, Allowing Bigotry: Auditing the Moderation of Hate Speech on Twitch
par: Shukla, Prarabdh, et autres
Publié: (2025)

Automated Coding of Communication Data Using ChatGPT: Consistency Across Subgroups
par: Hao, Jiangang, et autres
Publié: (2025)

ToxiTwitch: Toward Emote-Aware Hybrid Moderation for Live Streaming Platforms
par: Ansari, Baktash, et autres
Publié: (2026)

Efficient Toxicity Detection in Gaming Chats: A Comparative Study of Embeddings, Fine-Tuned Transformers and LLMs
par: Tereshchenko, Yehor, et autres
Publié: (2025)

ChatLog: Carefully Evaluating the Evolution of ChatGPT Across Time
par: Tu, Shangqing, et autres
Publié: (2023)

GAMEBoT: Transparent Assessment of LLM Reasoning in Games
par: Lin, Wenye, et autres
Publié: (2024)

HuixiangDou: Overcoming Group Chat Scenarios with LLM-based Technical Assistance
par: Kong, Huanjun, et autres
Publié: (2024)

ChatInject: Abusing Chat Templates for Prompt Injection in LLM Agents
par: Chang, Hwan, et autres
Publié: (2025)

Benchmarking LLM Guardrails in Handling Multilingual Toxicity
par: Yang, Yahan, et autres
Publié: (2024)

ROUGE-K: Do Your Summaries Have Keywords?
par: Takeshita, Sotaro, et autres
Publié: (2024)

PSK@EEUCA 2026: Fine-Tuning Large Language Models with Synthetic Data Augmentation for Multi-Class Toxicity Detection in Gaming Chat
par: Pulipaka, Srikar Kashyap
Publié: (2026)

Understanding Political Communication and Political Communicators on Twitch
par: Kim, Sangyeon
Publié: (2024)

When to Invoke: Refining LLM Fairness with Toxicity Assessment
par: Ren, Jing, et autres
Publié: (2026)

Research Community Perspectives on "Intelligence" and Large Language Models
par: Højer, Bertram, et autres
Publié: (2025)

On the Notion that Language Models Reason
par: Højer, Bertram
Publié: (2025)

Mapping Toxic Comments Across Demographics: A Dataset from German Public Broadcasting
par: Fillies, Jan, et autres
Publié: (2025)

Enhancing LLM-based Hatred and Toxicity Detection with Meta-Toxic Knowledge Graph
par: Zhao, Yibo, et autres
Publié: (2024)

VegaChat: A Robust Framework for LLM-Based Chart Generation and Assessment
par: Hostnik, Marko, et autres
Publié: (2026)

PLAYER*: Enhancing LLM-based Multi-Agent Communication and Interaction in Murder Mystery Games
par: Zhu, Qinglin, et autres
Publié: (2024)

NeedleBench: Evaluating LLM Retrieval and Reasoning Across Varying Information Densities
par: Li, Mo, et autres
Publié: (2024)

Towards Inclusive Toxic Content Moderation: Addressing Vulnerabilities to Adversarial Attacks in Toxicity Classifiers Tackling LLM-generated Content
par: Furniturewala, Shaz, et autres
Publié: (2025)

AutoDCWorkflow: LLM-based Data Cleaning Workflow Auto-Generation and Benchmark
par: Li, Lan, et autres
Publié: (2024)

Context-Aware Toxicity Detection in Multiplayer Games: Integrating Domain-Adaptive Pretraining and Match Metadata
par: Schurger-Foy, Adrien, et autres
Publié: (2025)

How Well Do LLMs Represent Values Across Cultures? Empirical Analysis of LLM Responses Based on Hofstede Cultural Dimensions
par: Kharchenko, Julia, et autres
Publié: (2024)

Triangulating LLM Progress through Benchmarks, Games, and Cognitive Tests
par: Momentè, Filippo, et autres
Publié: (2025)

UNITYAI-GUARD: Pioneering Toxicity Detection Across Low-Resource Indian Languages
par: Beniwal, Himanshu, et autres
Publié: (2025)

From Gameplay Traces to Game Mechanics: Causal Induction with Large Language Models
par: Jiwatode, Mohit, et autres
Publié: (2026)

"Only ChatGPT gets me": An Empirical Analysis of GPT versus other Large Language Models for Emotion Detection in Text
par: Lecourt, Florian, et autres
Publié: (2025)

Argument-Based Consistency in Toxicity Explanations of LLMs
par: Mothilal, Ramaravind Kommiya, et autres
Publié: (2025)