Understanding and Predicting Derailment in Toxic Conversations on GitHub

• URL: http://arxiv.org/abs/2503.02191v3
• Date: Wed, 19 Mar 2025 14:54:16 GMT
• Title: Understanding and Predicting Derailment in Toxic Conversations on GitHub
• Authors: Mia Mohammad Imran, Robert Zita, Rebekah Copeland, Preetha Chatterjee, Rahat Rizvi Rahman, Kostadin Damevski,
• Abstract summary: This study aims to understand and predict conversational derailment leading to toxicity on GitHub.<n>Based on this dataset, we identify unique characteristics of toxic conversations and derailment points.<n>We propose a proactive moderation approach to automatically detect and address potentially harmful conversations before escalation.
• Score: 6.343946534579351
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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.

Related papers

• Forecasting Communication Derailments Through Conversation Generation [28.51849747967488]
  We develop a fine-tuned model for predicting future communication derailments. Our method surpasses state-of-the-art results on English communication derailment prediction benchmarks.
  arXiv  Detail & Related papers  (2025-04-11T18:15:46Z)
• Interactive Dialogue Agents via Reinforcement Learning on Hindsight Regenerations [58.65755268815283]
  Many real dialogues are interactive, meaning an agent's utterances will influence their conversational partner, elicit information, or change their opinion. We use this fact to rewrite and augment existing suboptimal data, and train via offline reinforcement learning (RL) an agent that outperforms both prompting and learning from unaltered human demonstrations. Our results in a user study with real humans show that our approach greatly outperforms existing state-of-the-art dialogue agents.
  arXiv  Detail & Related papers  (2024-11-07T21:37:51Z)
• Knowledge-Aware Conversation Derailment Forecasting Using Graph Convolutional Networks [5.571668670990489]
  We derive commonsense statements from a knowledge base of dialogue contextual information to enrich a graph neural network classification architecture. We fuse the multi-source information on utterance into capsules, which are used by a transformer-based forecaster to predict conversation derailment. Our model captures conversation dynamics and context propagation, outperforming the state-of-the-art models on the CGA and CMV benchmark datasets.
  arXiv  Detail & Related papers  (2024-08-24T02:40:28Z)
• Outcome-Constrained Large Language Models for Countering Hate Speech [10.434435022492723]
  This study aims to develop methods for generating counterspeech constrained by conversation outcomes. We experiment with large language models (LLMs) to incorporate into the text generation process two desired conversation outcomes. Evaluation results show that our methods effectively steer the generation of counterspeech toward the desired outcomes.
  arXiv  Detail & Related papers  (2024-03-25T19:44:06Z)
• Conversation Derailment Forecasting with Graph Convolutional Networks [6.251188655534379]
  We propose a novel model based on a graph convolutional neural network that considers dialogue user dynamics and the influence of public perception on conversation utterances. Our model effectively captures conversation dynamics and outperforms the state-of-the-art models on the CGA and CMV benchmark datasets by 1.5% and 1.7%, respectively.
  arXiv  Detail & Related papers  (2023-06-22T15:40:59Z)
• ChatCoT: Tool-Augmented Chain-of-Thought Reasoning on Chat-based Large Language Models [125.7209927536255]
  We propose ChatCoT, a tool-augmented chain-of-thought reasoning framework for chat-based LLMs. In ChatCoT, we model the chain-of-thought (CoT) reasoning as multi-turn conversations, to utilize tools in a more natural way through chatting. Our approach can effectively leverage the multi-turn conversation ability of chat-based LLMs, and integrate the thought chain following and tools manipulation in a unified way.
  arXiv  Detail & Related papers  (2023-05-23T17:54:33Z)
• SpokenWOZ: A Large-Scale Speech-Text Benchmark for Spoken Task-Oriented Dialogue Agents [72.42049370297849]
  SpokenWOZ is a large-scale speech-text dataset for spoken TOD. Cross-turn slot and reasoning slot detection are new challenges for SpokenWOZ.
  arXiv  Detail & Related papers  (2023-05-22T13:47:51Z)
• Conversation Modeling to Predict Derailment [15.45515784064555]
  The ability to predict whether ongoing conversations are likely to derail could provide valuable real-time insight to interlocutors and moderators. Some works attempt to make dynamic prediction as the conversation develops, but fail to incorporate multisource information, such as conversation structure and distance to derailment. We propose a hierarchical transformer-based framework that combines utterance-level and conversation-level information to capture fine-grained contextual semantics.
  arXiv  Detail & Related papers  (2023-03-20T15:10:45Z)
• CoSyn: Detecting Implicit Hate Speech in Online Conversations Using a Context Synergized Hyperbolic Network [52.85130555886915]
  CoSyn is a context-synergized neural network that explicitly incorporates user- and conversational context for detecting implicit hate speech in online conversations. We show that CoSyn outperforms all our baselines in detecting implicit hate speech with absolute improvements in the range of 1.24% - 57.8%.
  arXiv  Detail & Related papers  (2023-03-02T17:30:43Z)
• Disentangling Online Chats with DAG-Structured LSTMs [55.33014148383343]
  DAG-LSTMs are a generalization of Tree-LSTMs that can handle directed acyclic dependencies. We show that the novel model we propose achieves state of the art status on the task of recovering reply-to relations.
  arXiv  Detail & Related papers  (2021-06-16T18:00:00Z)
• Who Responded to Whom: The Joint Effects of Latent Topics and Discourse in Conversation Structure [53.77234444565652]
  We identify the responding relations in the conversation discourse, which link response utterances to their initiations. We propose a model to learn latent topics and discourse in word distributions, and predict pairwise initiation-response links. Experimental results on both English and Chinese conversations show that our model significantly outperforms the previous state of the arts.
  arXiv  Detail & Related papers  (2021-04-17T17:46:00Z)
• Online Conversation Disentanglement with Pointer Networks [13.063606578730449]
  We propose an end-to-end online framework for conversation disentanglement. We design a novel way to embed the whole utterance that comprises timestamp, speaker, and message text. Our experiments on the Ubuntu IRC dataset show that our method achieves state-of-the-art performance in both link and conversation prediction tasks.
  arXiv  Detail & Related papers  (2020-10-21T15:43:07Z)

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.