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

• URL: http://arxiv.org/abs/2504.01534v1
• Date: Wed, 02 Apr 2025 09:21:41 GMT
• Title: Context-Aware Toxicity Detection in Multiplayer Games: Integrating Domain-Adaptive Pretraining and Match Metadata
• Authors: Adrien Schurger-Foy, Rafal Dariusz Kocielnik, Caglar Gulcehre, R. Michael Alvarez,
• Abstract summary: Traditional toxicity detectors focus on isolated messages, missing the broader context needed for accurate moderation.<n>This is especially problematic in video games, where interactions involve specialized slang, abbreviations, and typos.<n>We adapted RoBERTa LLM to support moderation tailored to video games, integrating both textual and non-textual context.
• Score: 0.9702021668898856
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: The detrimental effects of toxicity in competitive online video games are widely acknowledged, prompting publishers to monitor player chat conversations. This is challenging due to the context-dependent nature of toxicity, often spread across multiple messages or informed by non-textual interactions. Traditional toxicity detectors focus on isolated messages, missing the broader context needed for accurate moderation. This is especially problematic in video games, where interactions involve specialized slang, abbreviations, and typos, making it difficult for standard models to detect toxicity, especially given its rarity. We adapted RoBERTa LLM to support moderation tailored to video games, integrating both textual and non-textual context. By enhancing pretrained embeddings with metadata and addressing the unique slang and language quirks through domain adaptive pretraining, our method better captures the nuances of player interactions. Using two gaming datasets - from Defense of the Ancients 2 (DOTA 2) and Call of Duty$^\circledR$: Modern Warfare$^\circledR$III (MWIII) we demonstrate which sources of context (metadata, prior interactions...) are most useful, how to best leverage them to boost performance, and the conditions conducive to doing so. This work underscores the importance of context-aware and domain-specific approaches for proactive moderation.

Related papers

• Uncovering the Viral Nature of Toxicity in Competitive Online Video Games [0.4681661603096334]
  We analyze proprietary data from the free-to-play first-person action game Call of Duty: Warzone.<n>All of a player's teammates engaging in toxic speech increases their probability of engaging in similar behavior by 26.1 to 30.3 times the average player's likelihood of engaging in toxic speech.
  arXiv  Detail & Related papers  (2024-10-01T18:07:06Z)
• Analyzing Norm Violations in Live-Stream Chat [49.120561596550395]
  We study the first NLP study dedicated to detecting norm violations in conversations on live-streaming platforms. We define norm violation categories in live-stream chats and annotate 4,583 moderated comments from Twitch. Our results show that appropriate contextual information can boost moderation performance by 35%.
  arXiv  Detail & Related papers  (2023-05-18T05:58:27Z)
• Constructing Highly Inductive Contexts for Dialogue Safety through Controllable Reverse Generation [65.48908724440047]
  We propose a method called emphreverse generation to construct adversarial contexts conditioned on a given response. We test three popular pretrained dialogue models (Blender, DialoGPT, and Plato2) and find that BAD+ can largely expose their safety problems.
  arXiv  Detail & Related papers  (2022-12-04T12:23:41Z)
• Emergent Communication: Generalization and Overfitting in Lewis Games [53.35045559317384]
  Lewis signaling games are a class of simple communication games for simulating the emergence of language. In these games, two agents must agree on a communication protocol in order to solve a cooperative task. Previous work has shown that agents trained to play this game with reinforcement learning tend to develop languages that display undesirable properties.
  arXiv  Detail & Related papers  (2022-09-30T09:50:46Z)
• Beyond Plain Toxic: Detection of Inappropriate Statements on Flammable Topics for the Russian Language [76.58220021791955]
  We present two text collections labelled according to binary notion of inapropriateness and a multinomial notion of sensitive topic. To objectivise the notion of inappropriateness, we define it in a data-driven way though crowdsourcing.
  arXiv  Detail & Related papers  (2022-03-04T15:59:06Z)
• Contextual Games: Multi-Agent Learning with Side Information [57.76996806603094]
  We formulate the novel class of contextual games driven by contextual information at each round. By means of kernel-based regularity assumptions, we model the correlation between different contexts and game outcomes. We propose a novel online (meta) algorithm that exploits such correlations to minimize the contextual regret of individual players.
  arXiv  Detail & Related papers  (2021-07-13T18:37:37Z)
• CONDA: a CONtextual Dual-Annotated dataset for in-game toxicity understanding and detection [1.6085428542036968]
  CONDA is a new dataset for in-game toxic language detection enabling joint intent classification and slot filling analysis. The dataset consists of 45K utterances from 12K conversations from the chat logs of 1.9K completed Dota 2 matches. A thorough in-game toxicity analysis provides comprehensive understanding of context at utterance, token, and dual levels.
  arXiv  Detail & Related papers  (2021-06-11T07:42:12Z)
• Toxicity Detection: Does Context Really Matter? [22.083682201142242]
  We find that context can amplify or mitigate the perceived toxicity of posts. Surprisingly, we also find no evidence that context actually improves the performance of toxicity classifiers. This points to the need for larger datasets of comments annotated in context.
  arXiv  Detail & Related papers  (2020-06-01T15:03:48Z)
• Exploration Based Language Learning for Text-Based Games [72.30525050367216]
  This work presents an exploration and imitation-learning-based agent capable of state-of-the-art performance in playing text-based computer games. Text-based computer games describe their world to the player through natural language and expect the player to interact with the game using text. These games are of interest as they can be seen as a testbed for language understanding, problem-solving, and language generation by artificial agents.
  arXiv  Detail & Related papers  (2020-01-24T03:03:51Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.