arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2503.02191cs.SE
收藏

理解并预测 GitHub 有毒对话中的脱轨现象

Understanding and Predicting Derailment in Toxic Conversations on GitHub

Mia Mohammad Imran, Robert Zita, Rebekah Copeland, Preetha Chatterjee, Rahat Rizvi Rahman, Kostadin Damevski

AI总结:

该研究构建含脱轨点标注的 GitHub 有毒对话数据集,分析语言与互动特征,并利用 LLM 对话轨迹摘要实现早期脱轨预测,F1-Score 达 70%。

摘要:

软件项目的繁荣依赖于不同背景个体的参与和贡献。然而,有毒语言和负面互动会阻碍贡献者的参与和留存,并使新参与者疏远。主动式审核策略旨在通过处理已经偏离预期目的的对话,防止毒性发生。本研究旨在理解并预测 GitHub 上导致毒性的对话脱轨。为推动该研究,我们整理了一个新颖数据集,包含来自 GitHub 的 202 个带有脱轨点标注的有毒对话,以及作为基线的 696 个无毒对话。基于该数据集,我们识别出有毒对话和脱轨点的独特特征,包括第二人称代词、否定词以及“苦涩挫败”和“不耐烦”语气等语言标记,还有项目贡献者与外部参与者之间对话动态的模式。利用这些实证观察,我们提出一种主动式审核方法,在对话升级前自动检测并处理潜在有害对话。通过使用现代 LLM,我们开发了一种对话轨迹摘要技术,用于捕捉讨论的演变并识别脱轨的早期迹象。实验表明,为提供 GitHub 对话摘要而定制的 LLM 提示在预测对话脱轨时达到 70% F1-Score,相比一组基线方法有显著提升。

英文摘要:

Software projects thrive on the involvement and contributions of individuals from different backgrounds. However, toxic language and negative interactions can hinder the participation and retention of contributors and alienate newcomers. Proactive moderation strategies aim to prevent toxicity from occurring by addressing conversations that have derailed from their intended purpose. This study aims to understand and predict conversational derailment leading to toxicity on GitHub. To facilitate this research, we curate a novel dataset comprising 202 toxic conversations from GitHub with annotated derailment points, along with 696 non-toxic conversations as a baseline. Based on this dataset, we identify unique characteristics of toxic conversations and derailment points, including linguistic markers such as second-person pronouns, negation terms, and tones of Bitter Frustration and Impatience, as well as patterns in conversational dynamics between project contributors and external participants. Leveraging these empirical observations, we propose a proactive moderation approach to automatically detect and address potentially harmful conversations before escalation. By utilizing modern LLMs, we develop a conversation trajectory summary technique that captures the evolution of discussions and identifies early signs of derailment. Our experiments demonstrate that LLM prompts tailored to provide summaries of GitHub conversations achieve 70% F1-Score in predicting conversational derailment, strongly improving over a set of baseline approaches.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑